Notification emails cleaned up (LXP): Emails sent by the LXP no longer ask you to add an old toolwire.com address to your safe senders, no longer show a dated copyright line, and no longer call the platform “TILE”. Their footer now reads “This is an automated message. Please do not reply to this e-mail.” and ”© Praxis AI. All rights reserved.”Export the gradebook (LXP): The cohort Gradebook has an Export CSV button. The file holds the same table as the page, with the filters you chose. It is prepared in the background and emailed to you as an attachment, and the download link also appears in your messages.Fix — Putting a lesson back into a class (LXP): When a class’s only lesson was unticked in the class management grid and then ticked again, it came back without the class’s members, who had to be added to the class again. Ticking a lesson now puts it back for the class’s members, and ticking a lesson again no longer extends their subscription. Removing a lesson from a class still keeps each learner’s progress in it.Lab session emails end with the login address (LXP): The “Session Info” email sent when an instructor-led lab session is scheduled no longer ends with the retired connection test, troubleshooting guide and support address. It now ends with the address learners use to sign in to the lab.Instructor-led lab sessions can be named after the cohort (LXP): a lab session’s name and workgroup may now start with a digit, so a class can be scheduled under its cohort code (for example 2026-RTT-66-AWS). The scheduling page checks the name as you type and explains what is allowed: letters, digits, hyphens, underscores and periods; no spaces; no period at the end.Interactive labs open right away (LXP): Opening an interactive lab while another one is still open used to stop on “You already have an existing session” and ask you to log out first. The new lab now simply opens: the one that was still open closes, keeping everything it saved. Virtual labs with a desktop are unchanged.Fix — Markdown, CSV and macro-enabled Office uploads: Some
.md, .csv, .docm, .xlsm and .pptm files were refused as “Not supported”, depending on the browser or device that uploaded them. They now process like any other file of their kind. A file that was refused before needs to be uploaded again.Fix — A shared computer opened the previous learner’s lab (LXP): When two learners used the same browser one after the other — on a shared or classroom computer, or an administrator acting as one learner and then another — launching the same virtual lab could open the lab the first learner was still running, with their files. Each launch now checks whose lab it is: the second learner gets their own lab, and the first learner’s lab is left as it was.Amazon Nova models retired: the Amazon Nova conversation models (Nova 2 Lite, Nova Premier, Nova Pro, Nova Lite, Nova Micro) are no longer offered. A Digital Twin or assistant that was set to one now uses Claude Haiku 5.5 on Amazon Bedrock. Video generation with Amazon Nova Reel is unchanged.Usage limit emails: when a learner reaches the daily usage limit, the Digital Twin’s contact and the account manager get an email naming the learner and when they can use it again.Cloud Lab desktops reopen reliably (LXP): Reopening a Cloud Lab, reloading the page or pressing Reconnect now always opens the lab’s desktop. Before, a second launch in the same browser could stop on a “Recent Connections” page or show no desktop at all.Standard notification emails on every portal (LXP): Every LXP portal now has a complete set of standard notification emails — account activation, password reset and password change, new messages, grading, enrollments, certificates and report exports. Portals that were missing some of them now send them (for example, a password reset there now emails the new password), and the standard emails have a plain, consistent look. Emails a program has customized for its own learners are unchanged. On Arabic-language portals the emails are in English and Arabic.Calendars are read as events: Paste the link of a published calendar in a chat, for example the address Outlook gives you when you publish a calendar, and your Digital Twin now reads it as a list of events with their dates, times and places. Repeating meetings appear on each date they happen. A calendar file (.ics) added to your files is read the same way. From a link, Pria lists the events of the last 30 days and the coming year.Confirm it’s you before an approval from Canvas: When Pria opens inside Canvas for an administrator, approving or denying a connector tool that asks for approval now first shows Confirm it’s you and emails you a code. Enter the code, then choose Approve or Deny again. People without admin rights on the Digital Twin or its account decide as before. See More security for Canvas login.Google sign-in asks for per-file Drive access: When you connect Google from your settings, Google now also asks whether Pria may use the Drive files you open or create with it. This is Google’s narrowest Drive permission: Pria cannot see the rest of your Drive. If you connected Google before, nothing changes for you.The voice meter follows your Digital Twin’s voice (Cartesia): In a voice conversation with a Digital Twin that uses a Cartesia voice, the live voice meter — on the voice screen and in the sidebar — now moves while the twin speaks, not only while you do. When the twin’s voice EQ/compressor is on, loud syllables also come through cleaner.Joining a Digital Twin takes an open twin or an invitation: You can join a Digital Twin when it is open for joining, or when you have an invitation — an invite link, or its invite code. An invitation stops working when the person who sent it can no longer add members to the Digital Twin, and so does the approval of a request made through it. When that happens Pria says why in a message.Invite is offered to the people who can add members: Invite — on a Digital Twin’s card, in the gallery and in its settings — is shown to the people who are allowed to add members to that Digital Twin.Only administrators can join: In the Studio UI, the switch under Joining is now called Only administrators can join. It hides the Digital Twin from the Join list for everyone else, and invitations still work. Its old name, Admins approve new members, described something it never did.Credit notices by email: When a Digital Twin’s shared credits run low, or run out, Pria now emails the Digital Twin’s Contact Emails and its account’s Account Contact/Notification Emails, with a link to add credits. Each notice is sent at most once a day.Fix — Require email MFA for this user: Turning Require email MFA for this user on for someone whose two-step verification had been turned off earlier did not ask them for a code. Now their next sign-in asks for the code sent to their email.Fix — Respondent Email on a feedback: The Respondent Email entered when editing a feedback was not kept. It is saved now.Group cohorts by customer (LXP): On My Cohorts, people whose cohorts come from more than two customers can select Group by customer to see them under one heading per customer, in alphabetical order; each heading can be collapsed. The page remembers the choice in that browser. Reordering cohorts by dragging is paused while they are grouped.Easier-to-read cohort cards (LXP): On My Cohorts, the description and dates on each cohort card now sit on a softly blurred panel — darker on light themes, lighter on dark themes — so they stay readable over any cover image. Cohorts without a description no longer show “null”.New roles start in My Cohorts (LXP): When an admin creates a role, Learner Experience starts in now defaults to My Cohorts and Portal Features to My Journey (Cohorts). Both can still be changed before saving; existing roles are unchanged.Create your own Digital Twin: Once your personal Pria has answered 5 of your questions, you can create a Digital Twin of your own. Open the Gallery (in the Studio UI: Settings › Billing & Credits): a Create your own Digital Twin card shows how many you have asked, and after the fifth select Upgrade and create a Digital Twin. You’ll be asked to turn on two-step sign-in, then the creation wizard opens. Your account can create up to 3 Digital Twins. If you use Pria through your school or organization, ask its administrator to create one for you. See Create a Digital Twin.RAG + KAG by default: When your files have a knowledge graph, Pria now uses RAG + KAG Fusion when you ask in chat, unless you choose RAG. Every place where you pick how Pria searches your files now offers RAG next to RAG + KAG Fusion, and Pria keeps your choice: turning Search Only on or off, turning retrieval off and on again, or an administrator editing your account no longer changes it. In your personal space, turning on Enable KAG Fusion for my files also switches you to RAG + KAG Fusion. If you picked RAG before this update, pick it again — from now on Pria remembers it. See Knowledge.Tools Guidance: Your personal Pria now sends shorter instructions about its tools with each question, so each question uses fewer credits. To get the detailed instructions back — useful for research — turn on Tools Guidance under your tools in Tools (in the Studio UI: Settings › Tools).Admins — saving a person changes only what you edited: Saving a person in Users could undo changes made since you opened them: it could turn off two-step sign-in they had just turned on, or switch their file search back to RAG. Saving now changes only the settings you edited.Fix — bullet lists in answers: Bulleted lists in Pria’s answers showed numbers instead of bullets, and a list inside a numbered list lost its own numbering (i, ii, iii or a, b, c). Lists look right again.Fix — Studio UI Settings respond to a click: In the Studio UI’s Settings, the switches in Tools, the Revoke button in Security and the Personal file longevity (days) box in Knowledge didn’t respond to a click or tap. They do now.Welcome to your personal Pria: When you create your own account, a short welcome shows what you can do with your personal Pria — ask questions, upload files, manage tools and create assistants — and that it stays private: your files stay in your own IP Vault, and the AI models keep none of your data. Select OK, Let’s go! to start; it does not show again.Subagent plans finish on their own: An approved plan could stop partway. Your Digital Twin answered while its research workers were still running, and the remaining steps waited until you selected Resume. Plans now run each step as soon as the steps it depends on are done, through to the end. Research plans (investor or market research, reports, memos) now run this way too, like build plans. The final summary no longer asks again about choices you already made when setting up the plan, and it no longer says work was interrupted while it is still running.Word documents from your Digital Twin: Ask for a Word memo or report and your Digital Twin can now save it as a Word document (.docx), with headings, lists, tables and links, in chat or as a step of a plan. It can also read the Word and PDF files it creates, so a plan’s review step can check them.
Lessons with a virtual lab register their lab again (LXP): When an admin creates or saves a lesson that requires a virtual lab, the lab is now registered in the lab engine automatically, with its image and settings. The message “Course created successfully, but lab registration failed” no longer appears for that reason, and the lab does not have to be created by hand.Two-step verification per user: In Admin → Users, a user’s Security tab now has Require email MFA for this user and Revoke trusted devices — the same controls the new-user form already offered. Turning it off resets the person’s authenticator app and backup codes and signs out their trusted devices; their next sign-in goes straight through.Admins can postpone two-step verification from a course page: When an admin opens Pria from a Canvas course page, Strengthen your account security shows Remind me in 7 days again — Pria opens as usual and asks again after 7 days. Signing in to Pria directly still asks admins to select Enable MFA. See More security for Canvas login.File uploads: When the AI service is briefly unavailable while reading a file, Pria now tries again a few times on its own instead of marking the file as failed.Fix — “Enable MFA” works when Pria opens inside Canvas: An admin account without two-step verification that opened Pria from a Canvas course saw Strengthen your account security, but neither button worked there and no code email was sent. Now Enable MFA shows Confirm it’s you: select Send me a code, type the code from the email, and Pria turns on two-step verification and opens as usual. See More security for Canvas login.Admin accounts that sign in directly can no longer postpone two-step verification: When an admin account signs in to Pria directly, the Remind me in 7 days button is gone. They select Enable MFA to continue. Other users who are shown the reminder can still postpone it for 7 days. See Multi-Factor Authentication.Wide conversation: The new Wide conversation button at the top right of a conversation lets it use the full width of the conversation area; select it again for the usual centred view. Your choice is remembered, in the Studio UI too.The Assistants window opens where your assistants are: It opens on the tab that has assistants for you — your Digital Twin’s tab first, then Personal, then System (in your personal space, Personal, else System) — and remembers your last tab for each Digital Twin.New assistants go to the tab you are on: Add creates the assistant in the tab you have open. Assistants for everyone in a Digital Twin are added by its administrators; anyone else’s new assistant is saved to Personal, and the Assistants window says so. A new assistant now starts blank instead of copying the last one you opened.Disable Create Assistants for Users applies everywhere: When a Digital Twin admin turns on Disable Create Assistants for Users (in the Studio UI: Stop people creating assistants), only the people who manage its assistants can add new ones to it, whichever app they use.Digital Twin tray: Your favorite Digital Twins and your credit balance moved from the top bar into a tray under it. Select the arrow next to your current Digital Twin to open it: on top, the Gallery and a card about your current Digital Twin — the start of its About text, how many files and assistants it has, and your credits; point at a favorite and the card shows it instead. Select a favorite to switch to it, or select Gallery to see all your Digital Twins. The Accounts button left the profile menu.Your Digital Twins are easier to tell apart: A Digital Twin whose AI name was never set now shows its own name in the galleries and the tray, instead of “Pria”. On small screens the mouse wheel scrolls the twin gallery sideways, and on the Pricing page the Digital Twin card opens at full size; the button at its top right switches between full size and the normal view.Memory settings have their own tab: Your Profile has a Memory tab with the User Memory switch and Manage Memory…; the Memory item left the profile menu.KAG Fusion for your files comes first: In Your Profile › Knowledge, Enable KAG Fusion for my files is now the first setting under Sources, with a short suggestion when it is off. New accounts start with it on.Fix — KAG Fusion for your files stays on: Once you turn on Enable KAG Fusion for my files, it stays on; before, it could switch itself off again.About Pria: The About Pria window stays readable when you maximize it, and its picture now spans the full width.More security for Canvas login: When Pria opens inside Canvas for an admin account, it first shows Confirm it’s you and asks for a 6-digit code sent to the email address on the account (or from an authenticator app). Students are not asked. A verified device is remembered for 24 hours inside Canvas, and a Digital Twin that uses Authenticate with Canvas does not show the extra step. The screen links to More security for Canvas login, which explains who is asked and what to do if you get stuck.Fix — Google Classroom: Connecting Google Classroom now asks Google for the permission your Digital Twin needs to read your coursework. If Classroom did not work for you, connect Google again.Google services show what you allowed: A Google service now counts as connected only when you allowed every permission it needs. A Digital Twin connected only to Google Meet, for example, no longer offers Google Drive tools.Claude Sonnet 5.5 is the recommended model: In the model pickers, the Default badge on the Amazon Bedrock list now sits on Claude Sonnet 5.5 instead of Claude Sonnet 5, and a Digital Twin that follows the platform default now answers with Claude Sonnet 5.5. A Digital Twin that picked its own model keeps it.GPT-6.1 Sol: OpenAI’s GPT-6.1 Sol can be chosen as a Digital Twin’s model, for reading images and for summaries, and for every agent role. Its lowest Reasoning Effort is Low.Claude Opus 5 and Opus 5.5 for every agent role: Both can now be chosen for any agent role a Digital Twin admin sets, the conductor included. Claude Opus 4.5 is now marked deprecated: a Digital Twin using it keeps working, and the pickers hide it unless you show deprecated models.Claude Sonnet 5.5: Claude Sonnet 5.5, Anthropic’s newest Sonnet, can be chosen as the model of your Digital Twin, from Anthropic directly, through Amazon Bedrock or through OpenRouter. It answers faster than Claude Sonnet 5 and reads images. With Reasoning Effort set to None, it may write a short line such as “Let me look that up” before it uses a tool.Claude Sonnet 5 price: Anthropic kept Claude Sonnet 5 at $2 per million input tokens and $10 per million output tokens instead of raising it on September 1. Credits for conducted turns and image analysis on Claude Sonnet 5 now follow that price, on Amazon Bedrock, OpenRouter and the Anthropic API alike.Retired OpenAI image models: OpenAI no longer serves DALL·E 2, DALL·E 3 or GPT Image 1, so the model pickers mark them as deprecated. A Digital Twin or assistant that used one of them now makes images with a current model instead of failing.Answer a Digital Twin’s question in your own words: In a shared Google Chat space or Slack channel, a Digital Twin asks “Is it OK if I share that here?” before sharing something sensitive. Answer the way you would to a person — “yes”, “yes thanks”, or “yes, 2025” when it also asked which year — instead of typing a fixed phrase. If your answer is not a clear yes, it asks again instead of sharing.Tap to answer in Google Chat: Under that question, tap Share here, Send only to me or Don’t share — no need to mention the Digital Twin again. Only the person who asked can choose.Send only to me: The answer arrives in the same thread as a private message that only you can see.Fix — “yes, but send it to me” never shares in the space: If your answer asks for the details privately, the Digital Twin no longer posts them in the shared space. In Slack, a “sure” you say to someone else in the thread no longer counts as permission.Attach files to a task on your Projects boards: Open a task and use Add file… in its Files section to link files from your vault. The card shows them as small chips; click one to open the file. If you attach files to a chat and ask your Digital Twin to create or change a task, it links those files to the task and tells you it did.Move a card to another board, and switch a board’s layout: Drag a card onto another board’s tab to move it there. The switch button on a board’s tab turns a kanban board into a weekly planner or back, after you confirm; cards keep their dates and whether they are done.Two-step verification at sign-in: When two-step verification is on for your account, signing in now asks for the code from your email or your authenticator app before you get in. Turn it on from your profile under Two-step verification; a browser you have verified on is trusted for 7 days, so you are not asked again there.Stop ends a running agent cleanly: Pressing Stop while an agent is still working on a request now shows the task as stopped, not failed.Last Activity is shown by default on the Digital Twins and Users lists: The Last Activity column now appears without adding it from the column picker, as it already did on the Accounts list.A file’s expiry countdown restarts each time it is used: A file kept for a period (for example 90 days) now expires that many days after its last use, not after its upload. Pria answering with the file, a download, a shared link or the file appearing in a conversation all start the period again; opening the preview in Files does not. Only Forever keeps a file for good. The file card and the preview show the countdown, the date and the period selector, and a file with no countdown says why (Forever, starts when included in search, or no end date).Connected-service switches save one by one: In the Digital Twin editor, saving after changing a Google, Microsoft or Smartsheet switch keeps only the switches you changed. A Digital Twin admin is no longer refused a save over staff-only switches they did not touch, and after disconnecting a service the editor shows the real state of that service.Zip downloads finish cleanly or say why not: A cancelled bulk, collection or workspace download stops at once instead of saving a broken archive, and a download that fails part-way is cut rather than kept. A workspace export is now complete or refused with a reason (up to 20,000 entries and 32 folder levels) instead of stopping quietly at 2,000. A personal collection downloads only for its owner, and in a Digital Twin collection other people’s confidential files are left out of the zip and the listing.Test an MCP connector before you save it: Both connector editors (Edit Connector MCP and MCP Server Configuration) gain a Test connection button that asks the server for its tool list with the values in the form, then offers that list as a checklist for Tools Choice and Ignore Approval. A new connector starts empty; the examples are placeholders, not saved values.The Digital Twin editor saves only what changed: A save keeps the settings you changed since the last save, and Discard returns to the last saved state. The Credits dialog changes one number and the balance is never part of a save. Long-term memory, Read aloud, Twin workflows and Agent mode are reachable again, voice engine cards follow the platform-default engine, and a Digital Twin admin can name a new Digital Twin and choose its billing account on the create form.Admin lists: the same status pills and a plain activity note: The Accounts, Digital Twins and Users lists share the pills All · Active · Inactive (by status) and All · Has activity (has ever been used); the classic Assistants list filters by All · Personal · Instance · Account · System. An active row quiet for more than 30 days now reads “35 days ago” under its status instead of a warning; the warning and “idle 6+ months” appear only after six months, and the Last Activity dot follows the same rule.Your agent’s email approval list is yours alone: The list of people your agent may email is seen and changed only by you, and saving it names the Digital Twin it belongs to.Sign-in and invitation safety: A sign-in link can no longer change or create an account by mistake, and a request to join a Digital Twin is approved only by the person who sent the invitation.Your Google Chat conversations now appear in your conversation history: When you talk to your Digital Twin in Google Chat, each Chat thread now shows up as its own conversation in your conversation list on the Pria website, titled after your first message. Open it to read the whole exchange or to carry on the conversation on the website — your Digital Twin remembers what was said in Chat. If you rename the conversation on the website, the new name stays even as the Chat thread continues. Only your own messages and your Digital Twin’s answers to you are shown, even in a shared space. Earlier Chat conversations are added as well. Slack conversations are not shown yet.Your Digital Twin remembers important things you tell it in Google Chat: When memory is turned on for your Digital Twin, it can store what matters from your Google Chat conversations, just as it does on the website. Memories from Chat show on the conversation when you open it on the website. In a shared space, nothing is stored unless you confirmed sharing for that message.Fix — website memory now considers your Digital Twin’s answers: When your Digital Twin decides what to remember from a website conversation, it now looks at its own answer as well as your message.Fix — Google Chat and Slack respect your Memory setting: In Google Chat and Slack, your Digital Twin now respects your Memory setting (turned off means it neither reads nor saves your personal memory) and keeps your personal memory out of shared spaces unless you confirm. Files it saves from Google Chat or Slack are kept forever, unless you chose a “Keep if unused” period in your settings.Single sign-on users are no longer asked to change their password: When an admin sets Must change password at next sign-in on a user (for example after a bulk import with a temporary password), the request now applies only to sign-ins with an email and password. Someone who signs in with Google, Microsoft, Facebook, Apple or through their learning platform is not interrupted, and the requirement waits for their next email + password sign-in. A new per-user switch, Skip the password change on SSO sign-ins (on by default), restores the old behaviour when turned off.Import Users explains its password switches: Both Import Users wizards now show Must change password at next sign-in (on by default) and Skip the password change on SSO sign-ins (on by default), each with a one-line explanation of what the imported users will see.Fixed: a newly created assistant seemed not to appear: In the Assistants gallery, a new assistant is Personal unless you tick the sharing option when you create it, and the gallery was reopening on the Digital Twin’s tab, which lists only assistants shared with the twin, while the “created successfully” message was cleared at once. The gallery now opens on the tab the new assistant belongs to, refreshes the assistant pickers immediately, and keeps the confirmation visible.Fixed: a Digital Twin describing its own searches to the user: During long tool-based answers (for example several Google Drive lookups), a twin could tell the user things like “Let me search Drive” or mention a “search budget”. The instruction the twin receives at that moment now tells it to present only what it found and what remains open, never the tools, counts or search steps.Fixed: creating a Digital Twin in your own account: An admin who was not listed as a manager of their account saw “Only a manager or an admin of the target account can create an instance in it.” when creating a new Digital Twin, even inside the account they already administer. An admin whose Digital Twin cannot be joined without an invitation (Allow Joining set to Disabled) can again create a Digital Twin in that account, and move one into it. A Digital Twin still cannot be attached to an account its creator has no standing in.Agents: the two agent pages now point to each other: The Agents page’s sidebar has a new Synaps sessions link to your Digital Twin’s Synaps agent page, and that page’s left rail has a new Pria agents section listing your running and recent Agents sessions — click one to open it on the Agents page. The two pages keep their own sessions; this makes it easy to move between them.Fixed: the Synaps agent page lost its top bar after a refresh: Reloading the browser on the Synaps agent page showed a top bar without Admin, Agent, the Digital Twin switcher or your credits. It is now complete, as on the Agents page.Fixed: sharing a file that belongs to another Digital Twin in your account: In Files, a file shared across your account from another Digital Twin offered Rename and Delete but not Make Public or Include in AI Search. Both are now offered to the same people who can rename it.Fixed: downloading files as a zip: Downloading a collection, downloading several selected files at once, and the zip from Export my data all failed with an error message instead of a file since the July update. All three work again.Shared conversations show who said what: In a conversation where several people talk with the same Digital Twin — such as a group thread brought over from Google Chat — each person’s messages now appear in their own bubble with their name and photo (or their initials), instead of all looking as if you had written them. Your own messages stay on the right; everyone else’s appear on the left, grouped by person, with any files they shared shown under their message. The twin also knows who said what when it answers, and searching your history matches people’s names too. Anyone who opens a shared conversation link without signing in sees the other people as “Participant”, with no photos. This works in both the classic and the new interface.Clearer messages when an approval or invite link fails: When you open an approval link for a request that no longer exists, Pria now says so — “This request no longer exists” — and tells you what to do: ask the person to request access again, or have an administrator of the Digital Twin add them. An invite link that no longer matches a Digital Twin, and a lost connection, each get their own plain message too.Integration Wizard: code that starts where you paste it: The wizard now shows, beside the generated code, which sites this Digital Twin accepts, and warns you when none is listed yet. The web page, React, Flask and Canvas code starts only on a site listed in Public Authorized URLs; the file says so at the top.Fixed: The Flask page from the Integration Wizard now opens the twin; before, the widget could fail to appear. The Claude instructions now say where to find the MCP Server Secret and how to send it. Headless (no UI) now warns that it cannot be used when people must accept a privacy policy.
Canvas: a course connected to a disabled Digital Twin: Students cannot use Pria in the course. Teachers who open Pria from a Canvas LTI 1.3 placement see which Digital Twin is disabled and can disconnect it from the course — then reload and connect the course to another one — or hide Pria in the course.Canvas: show Pria again with one click: In a course where Pria was hidden, teachers now show it again from Pria itself.Changed: Picking a Digital Twin no longer takes a course away from a disabled one; the disabled Digital Twin is disconnected first. Only teachers and administrators of a Digital Twin can disconnect its course. In courses that use the Canvas theme integration, Pria does not open while the course’s Digital Twin is disabled; an administrator disconnects the course in the Digital Twin’s settings (Integrations › LTI Contexts).Canvas: a course connected to a disabled Digital Twin no longer blocks teachers: When the Digital Twin connected to a Canvas course is disabled (or its account is), teachers and administrators now see the “Let’s get you connected” chooser with a note naming that twin, and can pick another twin or create a new one — the course is connected to the twin they choose. Students see a message naming the twin and asking them to contact their teacher.A Canvas course connects to one Digital Twin only: Connecting a course that another active twin already uses is refused — from a Canvas launch with “This course is already connected to another Digital Twin”, and in the Digital Twin editor (classic or new) with a message naming that twin. Connecting a course that only disabled twins still list moves it to the twin you choose.Fixed: “Public Authorized URLs” and “LTI Contexts” with several entries in the new admin’s Digital Twin settings: Saving more than one entry in either list from the new admin’s Digital Twin settings (Configuration › Integrations) stored them as a single combined entry, which could block every Canvas launch of that twin. Both lists now save each entry separately, as the classic editor does.Procore connector: Staff email addresses and phone numbers in a project’s directory are now shown to Digital Twin administrators only. Other members still see names, companies, titles and roles, and every company’s business phone and email.Last Activity counts every way a Digital Twin is used: The “Last Activity” date of Digital Twins, accounts and users now includes meetings, avatar embeds, Slack, voice calls, uploads, scheduled workflows, MCP searches and agent computers — not only chat. Signing in or opening a page does not count. Digital Twins, accounts and users that were never used now read “Never used”, and once they are older than the inactivity threshold they are flagged, counted from the day they were created.Feature: Disabling or deleting an account now stops its agent computers; they can be started again after the account is re-enabled.Procore connector for Digital Twins: On the Connections page, a Digital Twin administrator can connect Procore with a client ID and client secret. When the twin’s Procore tool is switched on, members chatting with the twin can ask about the company’s Procore projects, submittals and documents. Procore is read-only, and visitors of a public twin page never get it.Faster LMS launches (LXP): Opening LXP content from Canvas or Moodle is quick again. The LXP’s own part of a launch now takes about ten milliseconds, down from several seconds — it had slowed over the summer as grading records built up. Grades still reach the LMS gradebook exactly as before.Moving a Digital Twin into another account now needs rights on that account: Only a manager of the target account can create a twin in that account or move a twin into it — being an admin of one of its Digital Twins is not enough.Security: Digital Twins created from an LMS launch stay in your own account: A twin created through the SDK onboarding or the in-app wizard is attached to an account only when the person creating it is a manager of that account, and the launch domain must match a registered domain exactly. Other twins start unattached until an account manager attaches them.Account secrets are never sent back to the browser: The account AWS secret key, Canvas client secret and Canvas faculty token are write-only. The account editor shows “Secret is set — leave blank to keep it”; a new value replaces it, and a Remove control deletes it on save. Clearing the AWS Access Key Id stops the account’s keys being used.Account AWS credentials reach every Digital Twin: The AWS key pair set on an account now signs the Bedrock model calls (conversation, embeddings, image analysis and generation) of every Digital Twin in the account that has no AWS keys of its own, so that usage bills to your own AWS account without setting keys twin by twin. A Digital Twin’s own keys still win. Video generation and transcription keep running on Pria’s own AWS account.Browse RunPod: On AI Models → Custom AI Models, a new Browse RunPod button opens the Connect RunPod card, where you connect a RunPod account and pick a hosted model. It is shown to admins who can add AI models.iPhone photos upload as pictures: HEIF, HEIC and AVIF photos (the iPhone default) are now handled as images and described like any other picture, instead of failing as if they were videos.A fallback conversation model: When a Digital Twin’s conversation model fails before it has said anything — over its usage limit, briefly unavailable, unreachable, or rejecting its key — Pria now answers with a fallback model instead of showing an error. Each Digital Twin can pick its own Fallback conversation model right under its conversation model (in the twin editor and in Instance Settings → Conversation). It is unset until you choose one. A twin on its own custom model falls back the same way.The usage card says which model answered: A turn answered by the fallback shows a note naming the model that could not answer and why. The conversation record keeps the model that actually answered, and billing follows it.Steadier retries: Every provider now judges a failed request the same way, waits as long as the provider asks before trying again, and stops retrying sooner when a fallback is ready. A reply that was cut off after it started is kept and marked, instead of being retried and repeated.A privacy policy now applies everywhere you meet your Digital Twin: When an organization sets a privacy policy for its account, everyone who uses one of its Digital Twins is asked to read and accept it before chatting or talking — in the classic interface, the new interface, Canvas, a public Convo guest link, and the avatar widget on a website. If the policy is ever changed, everyone is asked again. Voice conversations don’t start until the policy is accepted.Easier to read: The consent screen has been redesigned for clear, readable text and buttons in both light and dark mode.Read it again anytime: You can always go back and re-read the policy — in the classic interface from the menu under Privacy Policy, and in the new interface from Settings → Security.Guests stay on the guest page: Reloading a public Convo guest link page now keeps a guest on that guest page instead of dropping them into the full app.Fixed a blank page: Classic users on an organization with a privacy policy could see a blank page instead of the consent screen. This is fixed.Canvas course buttons land in the right conversation: A course button in Canvas that sends a question to your Digital Twin now opens that course’s own conversation first, so the reply shows up there instead of in whichever conversation happened to be open before.Clicking a course button while Pria is still loading now works: Before, a click that arrived before Pria had finished signing you in could fail. Pria now waits until it’s ready and sends the question then, instead of failing.Double-clicking a course button sends one question, not two: Clicking the same course button twice in a row now sends the question only once.Clicking two different course buttons sends both, one after the other: Clicking two different course buttons quickly now sends both questions, one after the other, and each answer stays with its own course instead of getting mixed up.A clear prompt when Pria has just been updated: If Pria was updated on the server while a student still had a page open, they now see a plain “Pria was updated — Reload” message with a Reload button, instead of an error screen.Deleting a collection moves its files to the Trash: Deleting a collection, together with any collections inside it, now moves their files to the Trash, where you can restore them, instead of removing them for good. The confirmation shows exactly how many files and collections are affected.Trash actions do what they say: In the new interface, Delete forever on selected files in the Trash now deletes them (it used to do nothing), after a confirmation that shows how many. Empty Trash in both interfaces now shows the exact number of files it will delete, and deletes exactly those. Files you aren’t allowed to delete, or that belong to someone else and are confidential, are left alone and no longer counted.Classic keeps your conversation going: In the classic interface, choosing an assistant from a page that embeds Pria, starting a conversation from the Canvas integration, or picking an assistant in Convo Mode now continues the conversation you have selected instead of opening a new one. The new interface still starts fresh by default.Rename or delete a conversation from another Digital Twin: Renaming or deleting a conversation listed under another of your Digital Twins in the sidebar or History now changes that conversation. Before, it could miss it, or change a conversation with the same number in your current Twin. Renaming a conversation you don’t have open no longer makes it the one Pria reopens next time.Retry keeps your attachments: When a message fails and you press Retry, Pria now sends it again with its attached files and the assistant you picked.Sharing a memory with everyone needs an administrator: Only administrators can share a memory entry with every member of a Digital Twin. Members still keep their own memories private and can stop sharing an entry at any time.End-of-meeting recap is on by default: When your Digital Twin attends a meeting, it posts a short recap when the meeting ends, unless Praxis has turned the recap off for that Twin. A setting change earlier this year had quietly stopped the recap for every Twin. Each recap is a summary and uses credits.Stop works on every Slack reply: Pressing Stop on a reply your Digital Twin is writing in Slack now always stops it, even when the reply is being written by a different server.Canvas students no longer see an Admin entry: Inside Canvas, the settings menu shows Admin to teachers only.An assistant’s own tools follow it into Convo Mode: When an assistant is limited to a chosen set of tools, those tools are now always available while you talk to it in Convo Mode — even ones that are otherwise switched off for voice conversations.Assistants that call an API now work in Convo Mode: The API-call tool is available during voice conversations by default, so an assistant that reads or submits data through an API — an assessment, a booking, a lookup — can do it while you talk to it, not only in text. Also, a voice turn no longer searches your files in the background when Knowledge is off — for the conversation or for the assistant running it — and when an assistant has its own collections, that is where a voice turn looks.Model lists refresh on their own: A model list that is already open in your browser now picks up newly added models within ten minutes, without reloading the page.Claude through OpenRouter reuses cached prompts: Claude Sonnet 5, Sonnet 4.6 and Opus 5.5 on the OpenRouter provider now reuse the cached part of a conversation’s prompt, as they already did on Bedrock and the Anthropic API, and every OpenRouter conversation stays on the endpoint that cached it. Credits go further on long conversations with these models. The two Sonnet models now use only OpenRouter’s zero-data-retention endpoints.Google AI Platform provider: Gemini 3.8 Flash can now be picked from a new Google AI Platform provider, served from Google Cloud’s Vertex AI with a Google Cloud API key — for organizations whose Google credentials live on the Cloud side rather than in Google AI Studio. Administrators set the key under Google AI Platform API Key in the Digital Twin’s configuration (the Gemini API Key stays for the Gemini Developer API).Claude Opus 5.5 through OpenRouter: Claude Opus 5.5 can now be picked from the OpenRouter provider as a conversation model, next to Sonnet 5 and Sonnet 4.6.Cached Gemini reads cost less: When a Gemini conversation reuses a cached prompt prefix, the cached part now costs fewer credits than before, because Google charges cached reads at 10% of its normal input price and Pria now passes more of that saving on. Credits go a little further on long Gemini conversations. Agent tasks pay Google’s cached rate directly.Gemini 3.8 Flash, Grok 4.7 and Grok 4.3 through OpenRouter: Administrators can now pick these three models from the OpenRouter provider as a Digital Twin’s conversation model or as the platform default — next to Claude Sonnet 5 and Sonnet 4.6, which were already there. They behave like their native counterparts (tools, images, thinking levels) and use only OpenRouter’s zero-data-retention endpoints.GPT-Live speaks first: A GPT-Live call now opens on its own as soon as it connects — your Digital Twin (or the assistant running the conversation) introduces itself, or picks up where you left off — instead of waiting for you to say something. A page that embeds the twin can still replace or skip the opening line, as with the other voice providers.GPT-Live follows the assistant’s lead: When an assistant is running, a GPT-Live conversation now hands every reply to it — your answers, choices and confirmations included — instead of answering on its own what sounded like small talk, and it no longer tells you it has no instructions. Switching assistants during a call reaches the voice layer too.Your assistant follows you into Convo Mode: Starting Convo Mode inside a conversation that runs an assistant now keeps that assistant’s instructions, on every voice provider. Before, on GPT-Live, Anam and Cartesia the assistant was silently dropped unless it had been checked in a Convo list most Digital Twins never filled in.“Restrict use of assistants”: The Convo setting formerly called “Allow switching assistant in Convo Mode” is now Restrict use of assistants, and it’s also in the Digital Twin’s settings under Voice. Off, every assistant can be used in Convo Mode. On, only the assistants you check can be used, and members can switch between them during a call.Assistant pictures in the Convo assistant menu: The in-call assistant menu shows each assistant’s picture, or the standard assistant icon when it has none, instead of the first letter of its name.Gemini voice shows who is speaking: In Convo Mode with a Gemini voice, the widget now lights green for the whole time your Digital Twin is talking and yellow while you speak. Before, green could switch off before the answer had finished playing, and yellow could stop showing altogether.“Tap to start talking” fills the screen: In the classic interface, the screen that starts a voice conversation now covers the whole window instead of only the chat area.Moving a collection to Personal: Only the person who created a collection can move it out of a Digital Twin into their personal space, and only when they may delete files in that Twin. The move is refused while the collection still holds files or sub-collections that belong to someone else.Security fixes: Tightened who can manage embedded avatar settings; who can add, move, upload into or change another person’s files and collections (moving a collection to another space no longer carries along files you aren’t allowed to move); and what files and records a desktop agent and the MCP connection can reach. Each stays within its own Digital Twin and respects confidential files.Pick the conversation before you send: In the classic interface, if you send a message while no conversation is selected, Pria now asks where it should go: Start a new conversation, or Continue your most recent one, shown by name. Before, the message could quietly start a new conversation that did not remember what you had said. Close the question and nothing is sent; your message stays in the box. If you have no conversations yet, a new one starts without asking.Going back to the default Digital Twin sticks: When you switch a conversation from an assistant back to the default Digital Twin, it now stays that way, in typed and voice replies alike, even after you reload or reopen the conversation. Before, the earlier assistant could quietly come back on the next reply.Meeting twins keep listening: In a Zoom meeting, a new person speaking now ends the previous turn, so your Digital Twin no longer goes quiet after a stuck turn. A question cut short is carried into the next reply, and very long text is shortened instead of refused.Helpers stay within bounds: A single request starts at most 15 helpers (more for an approved plan with many steps), and the lead helper stops when the request reaches its time limit, so a runaway task cannot keep spending credits.Voice and avatar replies start sooner: Your Digital Twin now notices you’ve finished speaking sooner. Twins created before the end-of-turn settings existed had waited up to 5 seconds. When the twin needs to look something up, it says so in one short line and then answers, without cutting that line off. On Gemini models, the voice conversation’s instructions stay cached between turns, so replies start faster and cost less.Voice conversations never wait on a slow tool: In Convo Mode, video avatars, embedded avatars and meetings, the twin waits at most about 6 seconds for its tools. A longer job, such as saving a file to the vault, keeps running in the background while the conversation continues, and the twin tells you the result on your next turn. OpenAI Realtime and xAI voice work the same way. Gemini Live voice is unchanged. Background work is billed to whoever started the session.A stuck voice reply recovers by itself: If the avatar goes 15 seconds without saying anything, it drops that reply and asks you to say it again instead of leaving you waiting. Anything it says resets the clock, and time spent waiting for you to approve a tool doesn’t count. Meeting bots follow the same rule. A reply nobody asked for, such as an unprompted meeting remark, just ends quietly.Pria on Canvas keeps its floating button: On Canvas course pages, Pria opens from its floating button again. The side panel docked to the right edge of the page is now opt-in: a Canvas administrator turns it on in the Pria loader.You approve every email a helper writes: Pria never sends email for you on its own: when a helper prepares an email, it waits on a card with Send and Discard.Meeting transcripts in every history view: When your Digital Twin attends a meeting, the full transcript now appears wherever you open that record: in Histories under Admin, and on the record’s shared page in both the classic and the new interface. Previously some of these showed the meeting as an empty conversation. Each view lists who said what and when, with the platform, duration and participants, and lets you copy or download the transcript. Administrators also see what the meeting cost in credits and whether it was charged.OpenAI GPT-Live for Convo Mode: A new voice option that listens and speaks at the same time, so conversations flow naturally and interruptions feel smooth. GPT-Live does the talking; your Digital Twin’s own model, files and tools supply every answer, and it keeps the user company while a longer lookup runs. Choose GPT-Live as the Realtime Model and pick a GPT-Live Voice. Conversation time is charged per second on top of the answering model. See Realtime Voice & Avatars.Choose how many passages Pria reads from your files: A new Number of Relevant Articles setting in Your Profile → Knowledge sets how many passages from your personal files Pria reads before it answers, from 1 to 15. It starts at 2, which keeps answers quick and saves credits; raise it when you want Pria to draw on more of your material. Administrators can change it for a person in Users → Edit → Knowledge. Digital Twins keep their own setting, and a Twin that never set one now also reads 2 passages, matching what its settings screen always showed.Pick your own GPT-Live voice: When a Digital Twin using GPT-Live leaves its voice unset (shown to administrators as User’s Choice), each member picks their own voice before starting Convo Mode.Typed messages in a GPT-Live call are answered aloud: With text input enabled, a message you type during a GPT-Live conversation now gets a spoken reply, and the reply appears in the transcript.Convo Mode follows the platform voice model: A Digital Twin (or a personal space) with no voice model of its own now starts Convo Mode on the platform default, including a Gemini default, with the matching voices. Before, it could start on the wrong provider and fail to connect.GPT-Realtime-2.1 is the new voice default: Digital Twins that follow the platform default now speak through GPT-Realtime-2.1. Twins set to a specific voice model keep it. GPT-Realtime-2.1 mini is also available at about a third of the cost.Voice Reasoning Effort now works with OpenAI voice: On GPT-Realtime-2 and newer, the Voice Reasoning Effort setting decides how much the model thinks before it answers aloud. It stays off by default, because thinking time is silence in a conversation. Older OpenAI voice models ignore the setting.Gemini 3.8 Live: Google’s newest live voice model, at the same price as Gemini 3.1 Flash Live. Tools work exactly as before.New image models: GPT-Image-2.5 Sunburst (precise edits) and Flare (fast everyday images), Gemini 3 Pro Image and Gemini 3.1 Flash-Lite Image, and Grok Imagine Image 2.0 and Image Quality.Retired Mistral models replaced automatically: Mistral has switched off Medium 3.1, Small 3.2, Large 2.1, Magistral, Devstral, Pixtral Large and Saba. Any Digital Twin, assistant or platform default using one moves to its current equivalent, usually Mistral Medium 3.5 or Small 4. Custom AI Models are left for an administrator to update.RunPod readiness follows the instance you are viewing: AI Models now checks each model’s own instance, even when your active Digital Twin is different. Missing or failed status checks show Status unavailable instead of leaving Checking… indefinitely. Viewing the list still does not start a GPU.Safer multi-instance model management: You can view readiness across selected instances, while RunPod connection changes require selecting one instance. Switching the selection clears old connection errors and unsaved key/confirmation state. Warm-ups and their release requests stay with their original instance.Held messages stay in the right Digital Twin: A message waiting for a RunPod model is not sent to a different twin if you switch instances during the wait. The ALN rubric and its 0–3 scoring scale are unchanged.A better RunPod GPU wait: An explicit warm-up or scoring request now rechecks the configured datacenters while it waits. If a warm-up is queued without a host and another approved datacenter has capacity, Pria can safely move its own warm-up there. It reuses a host that is already starting, avoids launching both datacenters speculatively, and shows the observed capacity, startup and model-loading phases. GPU availability is still subject to the provider; viewing status alone does not start a GPU.ALN stays on the 0–3 scale: The plan scorer keeps zero as a real score and rejects an incompatible scale rather than shifting the instrument to 1–4. Rubric-only scoring does not require anchors. A checklist made for an older rubric cannot silently override a revised one.Preview and resume a bake-off more safely: A read-only preflight lists the rubric, plans, requested models and blockers before requesting a GPU. Resuming a run checks that the inputs and scoring conditions still match. Missing models remain visible in reports; incomplete totals are kept separate, and quotes outside a dimension’s primary answer field are flagged for review without changing the score.A clearer Digital Twin interview: The creation wizard asks what you believe about your work and generates a compact persona covering identity, beliefs, voice, subject expertise and boundaries. Generate and Analyze can return complete text when using supported reasoning models.More conversational board controls: Twins with task-board tools enabled can create boards, update their columns and move tasks between boards. Weekly-board dates and carry-over are handled consistently by Pria, and cards created by a twin show their origin.The voice avatar fits phone screens: In Convo Mode the avatar no longer runs off the edge of the screen on a phone. In portrait it now leaves a margin on both sides, and in landscape it shrinks so the controls fit below it and the dark band above it is gone. Nothing changes on a laptop or desktop, where the avatar keeps its previous size.Two-step verification fits phone screens: When you enter the code we emailed you, all six digit boxes now fit inside the card on a phone; the last box is no longer cut off at the edge. On larger screens the card looks the same as before.Spoken answers are written for speech: When your Digital Twin answers out loud through its avatar, it now works from instructions meant for a spoken conversation. It no longer carries the rules for laying out a written answer — headings, tables, links, footnoted citations — which it could never say aloud anyway. You should notice answers that stay in the twin’s voice and get to the point sooner, and the twin still says a few words before it goes to look something up, so a spoken turn never goes quiet. Typed conversations and meetings are unchanged, and the twin still follows the same rules for reading its retrieved files.Voice conversations show where the context went: Opening a saved Convo Mode conversation now shows the same context breakdown as a typed one — how much of the context window went to the twin’s persona, its files, the conversation so far and the tools — instead of a single unlabelled block. This applies to conversations held from now on.The model name says which voice answered: A saved voice conversation now names the model that actually spoke. For a twin with an Anam avatar it reads Anam Response Model, the same name as the setting in Instance Settings, so the receipt matches what you configured rather than showing the twin’s typing model.Bring your invitation instructions into the meeting: When you ask your Digital Twin to join a call and review particular files or cover an agenda, it now keeps those instructions in the meeting’s context. This works for typed and spoken invitations. Named files must already be available through the twin’s permitted file tools; naming a local file does not upload it or grant access. Existing turn-taking, Poke and Hold controls are unchanged.Meeting assistants no longer block speech startup: Associating an accessible assistant with a meeting twin now works even when that assistant is not listed in the one-to-one Convo picker. If the assistant is unavailable or not permitted, the twin continues without that extra assistant context rather than losing its speech connection. The twin’s avatar and voice settings are unchanged. See Meeting Agent.A failed settings save tells you what happened: If a change in Instance Settings is refused, an inline notice identifies the setting and explains why the previous value was restored.Poke makes your meeting twin speak: Send the word poke in meeting chat or a direct message to request one normal spoken response — no wake word needed. If the twin is already responding or a participant is speaking, the request waits for the normal turn boundary instead of interrupting the twin. Hold cancels a pending Poke.Instance Settings: tool presets for your Digital Twin: The Tools section now offers the same presets as a personal account — None, Minimal, Media, Builder and All — with the number of tools each one leaves on. Picking one asks for confirmation, then switches the rest off for everyone in the Digital Twin; you can still switch single tools back on afterwards. A connection you configured — Canvas with its credentials, or Google and Microsoft while they are enabled for members — is never switched off.The action menu says how many tools your Digital Twin offers: The Tools entry now reads “For everyone in this Digital Twin - 12 on”, so you can see the size of the set without opening the settings.“Sources” is now “File Vault”: In the action menu’s Knowledge section, the file vault settings are named File Vault.Guest links: clearing and rollback fixes: If Convo is later switched off or limited to admins, an existing Convo Web Access Link can still be removed from Instance Settings, and a failed removal no longer shows the link as gone while it is still live.Guest links only when guests can use them: The Convo Web Access Link can no longer be set while Convo is switched off or limited to admins, since a visitor could never start a conversation on it. The field explains which switch to change, and a link that is already live in that state is flagged so you can clear it.Meetings now bill by the minute: Sending your Digital Twin into a Zoom, Google Meet, or Teams call as the Meeting Agent bills differently from a one-to-one Convo Mode conversation. For every minute the meeting bot is in the call, credits are metered for the avatar, the meeting bot, and live transcription — on top of the normal per-turn rule for whatever the twin actually says when it speaks. Digital Twins running on their own Anam account are not charged credits for the avatar’s minutes in a meeting; the meeting bot and transcription minutes still bill in credits either way. One-to-one Convo Mode conversations are unchanged — the avatar still adds no per-minute charge there. See Meeting Agent and Credits.Apply the avatar standard in one click: Digital Twins that speak through an Anam avatar have a new Apply the avatar standard button in Instance Settings, right under the Anam Response Model choice. It shows exactly which settings would change to the recommended avatar configuration — retrieval depth, chunk size, completion cap, immersive start, the recommended models — and applies them only when you confirm. A twin that already matches sees the button disabled.The voice says where it saved your file: When you ask your Digital Twin to build something into a named vault, the spoken answer now always starts with where the file was saved — and why, if it landed somewhere other than where you asked.Instance Settings: copy the Name and the Public ID: The General section now shows your Digital Twin’s unique Name (for example clarkey.praxislxp.com) and its Public ID, each with a button that copies it.Instance Settings: every screen explains itself: General, Personalization, Conversation, Voice, Knowledge, Subagents, Connectors, Quotas and Invite now open with a short About box that explains their features in plain words.Instance Settings: a clearer order: The sections now run General, Personalization, Conversation, Voice, Knowledge, Tools, Assistants, Subagents, Connectors, Quotas, Invite, Integration and Billing. Display Details moved into Conversation, since it changes what each answer shows, and Ignore user personal vault sits right under Long-term Memory in Knowledge.Instance Settings: Connectors: A new Connectors section shows how Google Workspace, Microsoft 365 and Canvas are set up for your Digital Twin, lets you change the two Canvas sign-in options, and opens the admin editor to configure connections and API keys.Instance Settings: add a custom AI model: Administrators allowed to add AI models can bring your Digital Twin its own model from the Conversation section.Instance Settings: Subagents has its own section: The subagent settings moved out of Tools into their own section. While subagents are off, the section shows only the switch that makes them available; the other options, including the model each subagent role uses, appear once they are on. Enabling subagents does not turn them on for anyone: each member opts in from the chat’s [+] menu.Instance Settings: find assistants faster: The Assistants section has a search by name and a “Show only enabled assistants” filter, and an assistant shared across your account now says which Digital Twin it comes from.Praxis Unified Credits: Wherever you see or add credits — the credit balance, Add Credits, Billing, your profile, and the messages shown when credits run out — Pria now names them Praxis Unified Credits.Instance Settings: small layout fixes: In Personalization, Persona mode now comes before the Digital Twin Instructions, and in Voice the Greeting delay field uses the full width.Copying a Digital Twin no longer repeats shared assistants: When an administrator copies a Digital Twin, the assistants shared across the account are no longer copied. The copy still uses them, and they no longer appear several times in every Digital Twin of the account.Files built by your Digital Twin open from their link: When a conversation builds a file for you, the link Pria gives you now opens without asking you to sign in, as long as the file is public in Files (built files are public unless you make them private). A link typed with the owner id in capitals works too.Built files keep their project folder in Files: A file built in one project no longer shares a name with a file of the same name built in another project, so nothing gets overwritten or shown twice. Files shows the plain file name; the project folder is kept underneath.“Save it in my Digital Twin’s vault” is honoured: If you ask a build to save its files in the vault of the Digital Twin you are talking to, and you are allowed to edit that twin’s files, the files land there (every member of the twin can see them in Files). Otherwise they land in your own files, and the answer says where they went and why. A twin-vault file is listed by the twin but not yet read into its knowledge.Security: only an administrator can change a Digital Twin’s tools: The list of tools the AI may use in a Digital Twin can now only be changed by an administrator who may edit that Digital Twin. Before, any member could change it through the API.Tools you choose (personal accounts): If you use Pria without a Digital Twin, you now choose which tools the AI may use in your conversations. Open Tools in the chat’s action menu, or Settings > Tools in the new interface. Pick a preset (None, Minimal, Media for images, video and audio, Builder for editing files, PDFs and web pages, or All), or switch tools on and off one by one, with a search box, category filters and a “Show only enabled tools” filter. Fewer tools make every answer lighter, faster and cheaper in credits. Until you choose, your account uses the recommended set (Minimal: your files, the web, and saving a file), plus the Google and Microsoft services you have already connected; other Google and Microsoft tools, and tools added later, stay off until you switch them on. In a Digital Twin, the tools stay set by its administrator; an administrator who may edit the Digital Twin finds them under Tools in the chat’s action menu too.Voice conversations are lighter: A voice conversation now offers the AI only the tools made for voice, so each spoken turn carries less text.A Digital Twin that ignores personal files ignores personal memory too: When Ignore user personal vault is on in a Digital Twin’s settings, the Digital Twin now also leaves out what members saved in their personal memory, in chat, voice and avatar conversations. It answers from its own instructions and knowledge, so every member gets the same Digital Twin. It does not save new personal memory either. Its shared memory still works, and members’ saved memory is kept for their other conversations.Tools lists show only what a Digital Twin can use: The Tools list in a Digital Twin’s settings, and in the admin editor, no longer shows tools whose feature is off for that Digital Twin (for example long-term memory, CRM, plan scoring, the meeting bot, or Google and Microsoft services that are not enabled for users). A line says which features hide tools. The AI is no longer told about those tools either, so every conversation carries less text.A searchable Tools list in the admin editor: The Tools section of the admin editor now lists tools like Instance Settings does, with a search by name, category filters and more tools loading as you scroll.A Digital Twin edits the files it made: A Digital Twin that ignores members’ personal files can now find, read and edit the files it saved itself, so a request to change a page it built changes that page instead of rebuilding it. When a file is somewhere the Digital Twin cannot open (another Digital Twin, the Trash), it says where instead of recreating it. It also no longer replaces a whole file it has not read first, even when you name the file: it reads it, then changes only what you asked. In a voice conversation it changes an existing file part by part, or saves a new one, instead of replacing it whole.Tool categories you can filter on: Every tool now has one clear category (Knowledge, Research, Documents, Creative, Memory, Assistants, Connections, Learning, Communication, Meetings, Scoring), so the category filters in the Tools lists find every tool.Meeting speech-input recovery: Meeting avatars now retry a failed microphone start and resume suspended audio capture. This addresses one possible reason a Digital Twin misses spoken prompts in Google Meet.Less silence on the first meeting reply: A twin can prepare its conversation context before being addressed and give a generated acknowledgement while an expensive first reply is being prepared. A brief grace period protects a reply that has not started playing, without preventing interruption once the twin is speaking.Clearer meeting-platform limits: Meeting avatars validate supported Zoom, Google Meet, Microsoft Teams and Webex links before trying to join. Slack Huddles and GoTo links are explicitly refused for interactive avatars rather than accepted for a connection that cannot provide the promised experience. Teams and Webex live checks remain pending.Security: you can only act on a Digital Twin you belong to: Creating an assistant in a Digital Twin, moving an assistant or a twin answer into another one, reading a twin’s variables and editing them now all check that you belong to that Digital Twin. Editing a variable only ever touches the variables of your own Digital Twin. Update requests that try to change protected fields through database operators are refused. Editing an assistant, a twin answer, a variable or an AI model now writes only that item’s own fields: the owner, the creation date and, for AI models, the server-measured data cannot be set from a request, an unknown value for a fixed-choice field is refused, and moving an AI model or a variable into another Digital Twin requires the right to edit that twin.Security: a lowered account type takes effect at once: When an administrator lowers someone’s account type, that person is signed out and signs in again with the new rights. Before, the old rights could stay active until the session expired.Files: “select all” and the file counters follow the same rule as the list: Selecting all files in a collection, and counting the files of a collection, now answer only for a collection you are allowed to open.Admin: AI models list honours a filter on several Digital Twins: Filtering the AI models list, or its export, on more than one Digital Twin now returns the models of all of them.Security incidents: withheld history says so: When the conversation history of an incident is in a Digital Twin where you are not allowed to read history, the panel now says so instead of “No history records found”.Files: the AI sees your vault, not your disk: When the AI lists or searches your files, it now sees exactly the files in your vault: nothing from the Trash, nothing that was already deleted, and no leftover copies. Every file tool the AI uses applies the same access rule as the rest of Pria: a confidential file of another member is never opened, edited or rendered, and a file shared across the Digital Twins of your account can be opened when it is listed. Knowledge switched to Disabled now closes the vault to the AI entirely for that conversation, and the AI says so instead of half-working; a build in a project workspace keeps its tools.Admin: stricter Digital Twin checks on lists, charts and files: The Digital Twin and account filters on the admin lists, exports and analytics charts now accept only a text list of ids, and any other form is refused with an error. Analytics charts, for conversations and for sessions, are cached separately for each administrator’s own scope. The conversation history attached to a security incident now shows only the Digital Twins where you are allowed to read history. The file list, its “select all”, the collections list and the vault health panel now check that you belong to the Digital Twin you ask for. The file details page opened from a citation now shows a file only to someone who may read it: its owner, a member of the Digital Twin that holds it, or anyone when the file is public. A confidential file stays with its owner.Background workers finish when they reach their tool budget: A background worker that reached its tool budget in the middle of a batch of tool calls on an OpenAI model now writes its result from what it gathered, instead of failing without an answer.Verify who a connector call is for: A new Verified identity page gives MCP partners the complete contract for the signed identity headers a Digital Twin sends to their connector: every header, the signing rule, ready-to-paste Node and Python verifiers, and a worked example to test against. It also explains which of the twin’s two MCP secrets to verify with. The MCP Server pages now link to it, and note that a twin’s voice turns may run on a different conversation model than its text turns.Page instructions get a spoken answer: When the page that embeds an Anam Digital Twin sends it an instruction, the twin now answers aloud, including before the learner has said anything or right after the greeting. The page is also told truthfully whether the twin replied.Fill the box in immersive view: A new Anam avatar setting, Fill the box in immersive view, makes the avatar video fill its box edge to edge in immersive view and in embedded twins, cropping the sides or the top and bottom, instead of showing the whole frame with a blurred border. It is off by default, so nothing changes until an administrator turns it on. For a tall, narrow box, also try Portrait avatar on the web app.Tool-heavy answers finish with an answer: When a reply uses many tools and reaches its tool budget, the Digital Twin now writes the answer from what it has gathered, listing anything it could not find under “Not found”. If it still cannot compose one, the reply ends with an honest line saying how many tool calls ran and inviting you to ask it to continue. Replies no longer trail off in “let me search…”.A rejected tool call shows as failed: When a tool (a Drive lookup, a web search, a connector) answers with an error, the reply’s tool details now mark that call as failed instead of successful.No claimed actions without a tool: The Digital Twin no longer says it logged, saved, updated or sent something unless a tool actually did so in that reply, and no longer promises to do “next” what it could do now. In a continuing conversation it also skips its opening greeting and status line and answers directly.See where an answer was cut off: The conversation InfoCard on the classic interface and the usage card on the 2026 interface show a line such as “Cut off after 20/20 tool calls” whenever a tool budget or a length limit ended the reply.Admin: Budget and Claims columns: In Admin › Histories, the Records list gains two Details columns. Budget says why a tool-heavy answer stopped early; Claims flags replies that state an action no tool performed, so they can be reviewed. Both have filter boxes.Admin: Tool calls per answer (cap): A new setting on the Tools section of the Digital Twin editor caps how many tool calls one answer may make before the twin must write the answer. Leave it at 0 for the platform default of 20; a twin can only lower the platform cap.The twin card’s info button works from the keyboard: On the Digital Twin gallery, the small “i” on each card is a real button now: it takes focus, opens on Enter or Space, and screen readers announce it as “More information”. The browser warning about a focused hidden element is gone.Manage Memory moved under the memory switches: In the action menu’s Knowledge → Memory section, Manage Memory… now sits beneath Enable User Memory and Enable Long-term Memory — the switches first, then the door to what they govern.The Favorites count updates when you star: The number on the ★ Favorites filter in the Assistants gallery now changes the moment you star or un-star an assistant, instead of after the next reload.Assistant tab counts show enabled of total: Each scope tab in the Assistants gallery now reads “10/12” when two of its twelve assistants are switched off for the twin (a plain “12” when none are), on the Personal, twin, account and System tabs alike. The Show disabled filter reveals the cards without changing the numbers.Cloning keeps your own role on the clone: When you clone a Digital Twin, the membership and entitlements you hold on the original are mirrored onto the clone — yours only, no other administrator’s. Twin administrators no longer need someone to grant them access to the twin they just created.Move your own assistants back to Personal: In the Assistants gallery, an administrator can drag an assistant they own from the twin or account tab back onto Personal (or pick Move to Personal from its ⋮ menu) to stop sharing it. Assistants owned by someone else cannot be taken back to Personal.Account tab count matches its cards: The Account tab listed only this twin’s account-shared assistants (and could list them twice) while its count included every twin under the account. The tab lists all of them again.Assistant cards highlight like Vault cards: Cards no longer grow on hover; they show a blue border on hover and focus, the same as files in the Vault.“New Conversation” is always a favorite: The built-in New Conversation assistant is pinned as a favorite for every user and twin, so it is always in the conversation action menu and the sidebar favorites. Its star cannot be removed.The gallery’s Configure button is gone: Administrators enable and disable assistants right on the cards now, so the button that opened Instance Settings → Assistants was redundant. That checklist is still available from Instance Settings.Fixed: the Assistants gallery crashed on open: Opening Manage Assistants could show an error page instead of the gallery. It opens normally again.Cloned twins get their own guest link: Cloning a Digital Twin no longer copies the Convo Web Access Link. The original and the clone never share a guest link, and saving the clone no longer fails because of it. The clone gets its own link, derived from the original’s; change it under Real-Time Combo → Convo Web Access Link.Unpublished assistants stay out of the switcher: An assistant that is still unpublished no longer appears in the Convo Mode assistant switcher, or in any assistant list except its author’s, whatever the “Allow switching assistant in Convo Mode” setting says.The “Inactive” assistant status is retired: Assistants have two working states, Active and Unpublished. The old “Inactive” state could not be set from the editor for a long time and only lingered as a badge and a filter; any assistant still carrying it becomes Unpublished on the first start after the update. Nothing changes for active or deleted assistants.The clone confirmation tells you the new guest link: After cloning a Digital Twin, the success message names the clone’s own guest address and reminds you to rename it and to review the integrations and assistants it inherited. A new admin-guide page, Cloning a Digital Twin, covers what a clone gets, what it does not, and what to review before sharing it.Move assistants by drag-and-drop: In the Assistants gallery, administrators can drag a card onto the twin tab or the account tab, or pick Move to <twin> / Move to <account> from its ⋮ menu, to share it at that level in one step. The card leaves the tab it came from and a short confirmation names the destination. Personal is never a drop target.Enable or disable an assistant right on its card: Twin administrators get an Enabled switch on every card and table row, plus Disable in <twin> / Enable in <twin> in the ⋮ menu. Disabled assistants dim and hide behind a Show disabled filter. The Configure checklist still works — and lists disabled assistants again, which it had stopped doing.The Assistants gallery opens on your twin’s tab: The strip is now four scope tabs — Personal, your twin, your account, System. Inside a Digital Twin the gallery opens on the twin’s tab (on Personal otherwise) and remembers the tab you pick. The All and Favorites tabs are gone; ★ Favorites is a toolbar filter that narrows whichever tab you are on.Stop works again: Pressing Stop while a reply is streaming stops it, on both the classic and the 2026 interfaces. One failed Stop no longer disables every later one on the same tab. The “Retry Stop” notice on a request that was moved to the background now stops that request, and a tab left open for a long time keeps its Stop.Less polling while a reply streams: The client no longer re-checks the server every five seconds for a stop receipt that cannot exist. After three empty checks it waits thirty seconds before asking again.Site links follow your published revision: Site actions in chat results and the workspace now use the site’s current published view instead of an older source-file URL. Private sites still offer the authorized editor rather than a public link; nothing is made public automatically. File actions are labeled Open source and Copy source link, and existing saved source links keep their original meaning.Clearer site editing: The site editor no longer labels its edit counter as a content version. Your unsaved site-settings choices survive a refresh, and links and controls stay with the right account and project.Research starts and chat recovery stays with the right turn: Corrects a pre-plan researcher startup failure and keeps the sidebar’s worker list tied to the displayed request, so an earlier researcher does not appear as an extra current worker. When a completed reply’s final connection is lost, chat can recover using exact server-confirmed completion evidence instead of trusting a connection event alone. This does not retroactively clear older stuck requests.Clearer Stop notices: A request that cannot be tracked no longer shows a misleading “Retry Stop” notice. Notices follow the 2026 interface styling, keep a readable sentence and an accessible Retry Stop button, and stay actionable when the status cannot be confirmed.Check tasks off on your Projects boards — and ask your twin to: Every card on a Projects board now has a check control. Tick it and the card is marked done where it sits, struck through — on a weekly planner it stays on its day, on a kanban board it also moves to Done (and dragging a card into Done marks it done; dragging it out re-opens it). Hide completed tucks finished cards away per board, and Completed (N) opens a list of everything you have finished on that board, with your notes and the date, and a Re-open button. Rolling a weekly planner to a new week now carries forward only the tasks still open. Your Digital Twin can do the same: “mark them both as done” checks the tasks off, “what are my tasks for today” lists only what is still open, and “what did I finish this week?” shows the completed ones. Removing a card is now a separate action from finishing it.Your Digital Twin can now set up and reshape your Projects boards: On Digital Twins where the CRM switch is on, Praxis Team members can ask their twin to create a board (“create a board for next week” builds a dated Monday–Sunday planner), rename it or move it in their board list, add, rename, reorder or remove lists on a kanban board, move a task between lists, and roll a weekly planner to another week — open tasks are carried forward to their due day or to the new Monday, never dropped. Weekly boards created from the Projects page are now dated by the server too, so the week is always right whatever your time zone. Cards the twin added carry a small twin chip so you can tell them from the ones you typed. Boards can be renamed or deleted from their tab, and a task with a date lands on that day of a weekly planner when you add it.Choose how easily members can interrupt a Gemini voice: A new Interruption Sensitivity setting in Instance Settings → Voice (and the admin twin editor) controls how readily a Gemini Live twin stops talking when a member speaks over it. Low, the existing behaviour and still the default, needs a clear voice before it yields, so classroom noise doesn’t cut Pria off. High lets a member interrupt with a quiet word, the way Gemini behaves out of the box — the better choice for one-to-one headset conversations. Nothing changes for any twin until an admin switches it.Convo Mode’s “listening” light now works on Gemini voices: When your Digital Twin runs on a Gemini Live voice model, the yellow highlight around the conversation control and the avatar — the one that shows Pria is hearing you — never lit up, even though your words were being transcribed correctly. The indicator now follows your microphone directly instead of waiting for the transcript to come back from the server, so it lights the moment you start speaking and clears when you stop, exactly as it does on the other voice providers. Muting still shows red, and the twin’s own speech still shows green.No “save to search” offer when a build produced nothing: When a build finishes without creating any files, the Done panel no longer asks whether to add them to search — there is nothing to add. Until now it showed “No files were generated” directly above an offer to index “0 build artifacts”, and choosing either answer recorded a decision that did nothing and then left the panel reading “Saved to search ✓ (0)” permanently. Builds that do produce files are unchanged, and a decision you already made on one of those is still remembered.A build receipt no longer appears without the request that made it: Asking for work to be handed to a subagent directly could leave a stray “Done — your project is ready” panel in the conversation with no question above it. That panel was attached to an internal record that carries the build’s state rather than to anything you typed, so it could never show your request. Those internal records are now kept out of the conversation entirely; your request and its answer appear as a normal exchange. Your files are unaffected and remain in the vault folder the build wrote them to.Your twin answers honestly about what it is: When someone asks a Digital Twin whether it is a person, an AI, or conscious, it now says plainly what it is — in its own voice, without claiming feelings or inner experience it does not have — and then carries on in character. It also stops retreating to “as an AI I don’t have opinions” on questions of taste, judgement or preference, and answers the way its character would. Twins that stay in character (persona mode) go further: on questions of meaning, values, feelings, hope and freedom they speak from the stance their instructions establish, and where their instructions are silent they decline the way their character would rather than switching into a neutral disclaimer. Nothing about safety behaviour changes, and a twin will always tell someone it is a digital twin when asked.A twin given instructions for the first time starts in character: Writing a Digital Twin’s instructions is how you give it a character, so a twin that receives its instructions for the first time — in Instance Settings › Personality › Digital Twin Instructions, or from the admin console — now starts with persona mode already on, instead of needing the switch beneath it found and turned on separately afterwards. Existing twins that already had instructions, and whose persona mode had never been set either way, were switched on too. A twin whose persona mode was deliberately turned off stays off, and twins with only a few lines of instructions were left alone.A website can guide a live conversation (SDK): A page that embeds your Digital Twin can now speak into a conversation that is already running — either as the learner, or as the page itself guiding what the twin says next, for example when someone opens a particular lesson. Guiding the twin is off until you allow it: Let the embedding page guide live conversations, in the instance settings beside the transcript sharing switch. Only the page your twin is embedded in can do it, and those turns are billed like any other. The page can also choose the twin’s opening line, or skip the greeting, and is told when a conversation is ready to be spoken into instead of having to guess.Typed messages reach avatar twins: In the classic interface, typing a message during a voice conversation with an avatar twin (Anam or Cartesia) did nothing — the box cleared and the message was never sent. Typed messages now reach the twin on every provider and are treated exactly like speaking them out loud.Importing users never edits an existing account: When you import a list of users (Admin › Users › Import) and an email already belongs to an account, the import only adds that person to your Digital Twin, with the role chosen in the import. Their account type is raised if the import asks for a higher one and is never lowered. Everything else on the account stays as it is: credits, status, plan, the Digital Twin they currently use, their name, password and MFA. Admin › Users lists people by the Digital Twin they currently use, so an imported existing account appears in your list once the person switches to your twin. To change anything else, open the user in Admin › Users.Tighter checks on editing accounts (admin): An administrator can edit an account only on a Digital Twin they manage: the one the account currently uses, and any twin they move it to.Subagents are now a personal choice (classic UI): An administrator authorizes subagents for a Digital Twin (Instance Settings › Subagents, or the admin editor) and can restrict them to admins with the new Admins only switch. Once authorized, every member sees Subagents in the chat + menu and turns it on for themselves — the choice is saved per twin on your membership. While it is on, a mode control (Auto / Basic / Advanced / Expert / Mythical) sits in the message box next to the Convo button so you can change how much autonomy Pria takes on each request; your pick is remembered. Members who have not turned it on keep single-agent conversations even when the twin allows subagents. The 2026 interface is unchanged.Assistants stay within their Digital Twin: A conversation can only run on an assistant you could pick from the Assistants list — a system assistant, your own personal assistants, the current twin’s assistants, or an account-shared assistant from another twin on the same account. A request that names an assistant outside that set (for example one carried over from a previous twin, or an assistant that has since been deleted) now runs on the standard New Conversation assistant instead of failing or using the other twin’s persona, and switching twins clears the voice assistant picked under the previous one. Earlier conversations that had been recorded against an out-of-scope or deleted assistant are now shown under New Conversation.Subagent turns no longer block the chat (classic UI): when a request is being handled by subagents you can keep chatting. Sending a new message hands the running work to a “Still working” block above the conversation — with its live agent panel and a Stop — and your new message is answered right away. The subagent answer arrives as its own message when it finishes. Reloading the page brings the running work back as the same block.Composer clean-up (classic UI): the red Stop button in the message box is gone — stop a streaming answer with the Abort control under the message, and end a voice session from the Convo controls.Classic sidebar: Settings section removed: The sidebar’s collapsible Settings section duplicated the input + menu, and its collapsed header could show a stray “Instance” line beneath it. Instance and Personal settings live in the + menu (Settings → Instance / Personal); the account Privacy Policy now sits under More.Subagent activity matches the classic transcript: In the classic UI the subagent panel now reads like the other transcript rows — a round agents avatar, a Subagents Details: (N) summary you expand like Tool Details, and the same bordered body — instead of a separate card. The summary also shows the mode the request ran in (Auto, Basic, Advanced, Expert or Mythical) and, on hover, whether it came from your pick in the message box or your saved preference.Subagents Details replays every step: In the classic UI, expanding Subagents Details on a finished reply now shows the steps that produced it, in order — how the request was routed, which model orchestrated it, each subagent it started (with the task it was given and the agent’s card right under it), what it collected and verified along the way, the synthesis, and the model that wrote the answer — instead of only the agent cards.Subagents Details shows where the time went: On new replies handled by subagents, the steps replay carries real timings — how long routing, orchestration and the final answer took, how many rounds the orchestrator ran and how much of its time was spent waiting on agents, a Waited line for each pause and which agent it waited for, how long each agent sat in the queue before starting, and the orchestrator’s own narration lines under the Orchestrate step. Earlier conversations keep the step list without the timings.Subagent efficiency (admin): The Charts tab of the Histories admin page gains a Subagent efficiency section for the last 31 days: for each model and mode, how many turns ran, how long they took, where the time went, and how many agents each turn used. Digital Twin admins see their own twin.Conversation details expire after 180 days: Your conversations stay complete for as long as you keep them — the question, Pria’s answer, which models answered, and the usage and credits recorded. What is removed after 180 days is the working detail behind an answer: the full text of each tool call and its result, the transcripts of the subagents that worked on it, the passages retrieved from your vault, Pria’s thinking and the memories it recalled. The rows that used to hold those details now say “Details expired after 180 days” and keep their counts (how many passages, tools or thinking rounds there were). Administrators see the cleanup routine’s last runs on the System Health page (System → System Health → Cleanup): the nightly prune and the weekly storage-health pass.System assistants can no longer be edited from the chat: The chat + menu and Manage Assistants no longer offer Edit for a system assistant (one that comes with Pria and belongs to no user and no Digital Twin).One usage breakdown per message: The usage card’s Pricing tab now lists every lane of the reply — the router hop, the orchestrator, the conversation model and each subagent — with tokens in/out, credits, tools and time on one table, and its total shows the credits billed. The separate Subagents tab and the “cheaper than a single premium-model pass” line are gone, and the classic Subagents Details row no longer repeats the receipt.Sign in with Apple: You can now sign in to Pria with your Apple ID — on the iOS app and on the web login page, where Apple sits beside Google, Microsoft, GitHub and Facebook. If you use Apple’s “Hide My Email”, Pria keeps working through Apple’s private relay. If you already have a Pria account under the same email, signing in with Apple simply connects it; you do not get a second account.Dragging a personal file to the Account vault now works: Dropping a file or a collection from My Files onto the Account tab moved the counters as though it had worked, but the file never arrived and the counts snapped back a moment later. Account files live in your instance and are shared across the account, so the move now joins the file to your Digital Twin and shares it in one step. The same fix applies to the bulk Move to Account action and to whole collections, whose files follow the collection.Edited file content appears immediately in the preview: After Edit Content › Save on a text or Markdown file, the preview kept showing the version from before your edit until you closed and reopened it. It now repaints with what you just saved, while the file is re-indexed in the background as before.Connector approvals inside delegated tasks: When Pria hands work to one of her agents and that agent needs a connector tool you have set to require approval, it no longer simply goes without. The agent’s card reads “waiting for your approval” and the request appears under that agent’s activity, in both the classic and the new interface — approve or decline there, or from the pending list in another tab, and the agent carries straight on with the real result. An agent waits up to three minutes. A declined or timed-out call is shown as a failed step rather than a successful one, and the outcome is recorded on the saved message like any other approval. While a plan is building, answer from the waiting agent’s own activity in the build panel; if Pria herself rather than one of her agents needs approval during a plan build, no card appears yet and that step waits out its three minutes without running.Connector approvals stay in sync across tabs and after a reload: A decision on a connector-tool approval card — Approve, Approve for this conversation, or Deny — now updates every open tab, not just the one where you decided: the card used to simply disappear the moment a decision landed, leaving other tabs (and a reloaded page) showing nothing and leaving you unsure whether the tool actually ran. It now shows the recorded outcome in place, with no buttons, wherever the card is open. The tier-upgrade suggestion pill is also now readable in classic dark mode, matching the fix already shipped for the approval card itself.Connector approvals in xAI and Gemini Live voice conversations: The last two voice modes that could not ask now do. When the twin needs approval to run a connector tool, the microphone pauses and the approval card appears — in the transcript, or over the conversation when you are in the compact bubble, the immersive view, or have transcripts turned off. Approve or decline there and the conversation carries on with the real result. In these two modes Pria cannot say the request out loud, so watch for the card; you have 45 seconds. Approve for this conversation is offered when the call is bound to a conversation thread, and if you hang up or reload while a request is waiting, it is cancelled and the tool does not run.Connector approvals now work in voice conversations: In an Anam or Cartesia voice conversation, a connector tool that needs approval no longer just fails to exist. Pria tells you out loud that she needs permission, names the tool and the connector, and puts the same Approve / Deny card in the live transcript — in both the classic and the new interface. Answer, and she carries on with the real result in the same breath. OpenAI Realtime conversations ask too, answered right in your browser (that one is not saved to your approval history, so it cannot be approved from another device). xAI Realtime and Gemini Live conversations do not offer approval-gated tools; their other connector tools now work there for the first time. ElevenLabs conversations will say the approval is not available in that channel and ask you to try again from the Pria chat.Approve a connector tool before it runs: Connectors with Require approval switched on used to hold their tools back entirely — the model was never told they existed. Now the model can ask: a card appears in the conversation naming the tool, the connector and exactly what it would run, with Approve, Approve for this conversation and Deny. Nothing runs until you decide, and the conversation carries on with the real result once you do. The card survives a page reload, a second tab and a second device, and the decision is recorded on the message so you can see later what you allowed. On OpenAI models using their built-in connector support, approval-gated calls used to fail silently — they now ask in the same way. Voice conversations do not show the card yet; there, tools that need approval are simply not offered.MCP connectors work on every model with tool support: A Digital Twin’s connectors (Edit › Connector MCP and Tools) were only used when the conversation model was an OpenAI model; on Claude, Gemini, Mistral or Grok the connector was silently ignored. Pria now connects to the MCP server itself, so the same connectors work on every conversation model, in text chat and in Anam, Cartesia and ElevenLabs voice conversations. Tools run with the same per-server credentials and the same signed identity headers as before. Connectors with Require approval enabled now offer their tools too, gated by the approval prompt described above.New interface no longer demands a course launch from a signed-in user: On phones, and after a Google one-click sign-in inside a Canvas panel, the new interface could show “LMS context required” to someone who was already signed in on a personal account, where the classic interface simply showed the app. It now behaves like classic: that notice appears only when there is no signed-in session at all, and requiring Canvas authentication remains something enforced only on SDK launches from Canvas.Long-term Memory is for everyone once it is on: Switching Long-term Memory on for a Digital Twin, from Instance Settings, the action menu or the admin editor, now also sets Admins only off and the Default Memory Mode to Long-term Memory in the same save, so members get it immediately instead of inheriting the old admins-only, classic-mode defaults. Administrators can still narrow it afterwards.Role Model Pins pick from the model catalog: In Instance Settings › Tools, each subagent role (Planner, Designer, Coder, Tester, Writer, Researcher, Agentic Loop) is now chosen from the same model selector used elsewhere, listing only the models suited to that role, with Default keeping the platform default. No more typing model ids by hand. The Integration wizard’s footer also fits on phones now.Read-aloud voices match the speech model: Choosing Verse or Ballad as the read-aloud voice on a twin using the default speech model made every Speak silently fall back to the browser voice, and the Preview button spun and played nothing: those two voices only exist on a newer speech model. The Read-aloud voice picker (Instance Settings, the admin editor and your own Playback voice) now lists only the voices your speech model can speak, adds Fable, Nova and Onyx, and flags a saved voice the model cannot speak as playing as Alloy. Preview shows a clear “Couldn’t play” message on failure, and Speak now tells you when it had to use the browser voice instead of the natural one. The Speech model can now be chosen right there in Instance Settings › Voice, under the natural-voices switch and above the voice, so the two are set together.Join a Digital Twin on your phone: The “Join this Digital Twin” dialog now fills the screen on phones, with the twin’s banner at the top, the About text scrolling in the middle, and Cancel / Join Now pinned at the bottom where your thumb is — instead of floating mid-screen above empty space. On tablets and desktops the dialog is unchanged.Profile avatar aligned in the top bar on phones: The profile picture (or the placeholder icon when you have no picture) at the top right of the classic interface sat slightly below and to the right of its white disc on phones, so the disc and its shadow looked offset. It is now centred.Confirmation before lowering a platform administrator: In Admin › Users, changing a platform administrator’s account type to admin or user now opens a confirmation that spells out what will happen: platform-wide administration is removed and, on save, every one of their memberships is changed too (admin entitlements cleared when changing to user). Cancelling keeps the account as it was.Public twin pages no longer ask visitors for Canvas authentication: A Digital Twin that requires Canvas authentication for its Canvas launches could not be opened through its public web page (
/twins/<name>): every visitor was refused with “Access to Canvas LMS requires a valid course Id”. Canvas authentication is now enforced only on Canvas launches; a visitor arriving through the twin’s public page is an anonymous guest with no Canvas course to validate and is let in as before. Canvas launches, and any attempt to use the guest entrance to sign in as a named Canvas user, are gated exactly as they were.Embedded-avatar conversations are now recorded and billed like every other dialogue: Conversations held through a Digital Twin’s embedded avatar widget now appear in the twin’s Histories, attributed to a visitor account created for that visit, with the credits each exchange used. Those credits follow the same rules as any conversation: the twin’s pooled balance, automatic top-ups from the parent account, and any usage limits you have set (per user, per twin, or per 24 hours) all apply to embedded visitors, and the usage reports include them. Visitors who open the widget but never speak are cleaned up automatically. A new Credit Audit view under Admin › System shows, for every twin that pools credits, a daily check that the credits leaving its balance match the credit ledger, with a Run yesterday button to compute a day on demand.Voice transcripts beside the avatar on larger screens: In the classic interface, when a Digital Twin shows transcripts during a voice conversation, tablets, desktops and phones held sideways now place the transcript beside the avatar with the call controls and the message box directly under it, instead of stacking everything in one narrow column. On phones held upright the controls move to the bottom, within thumb reach. The avatar keeps its proportions at every size and with every voice provider. A new Hide transcript button collapses the transcript when you want to focus on the avatar; it comes back expanded on your next conversation. The transcript and the message box are now readable over any background picture, the transcript can be scrolled with the keyboard, and every control is reachable with Tab.Digital Twin sign-in links now work while you’re already signed in: Opening a twin’s sign-in link (a bookmark, an invitation) with a session still active used to leave you on the twin you last used and wrongly warn that you had no access to the one in the link. The link now takes you straight to that twin whenever you’re a member, and the “No access” notice only appears when your account really isn’t allowed in — and says whether the twin is closed to you or simply unavailable. Choosing Log Out & Switch Account from that notice now brings you back to that twin’s sign-in page so you can sign in with the invited address.Live voice transcripts for embedded twins: A page that embeds a Digital Twin through the Pria SDK can now receive the conversation’s transcript live — what the learner says and what the avatar answers, as it happens, for every voice provider — and build its own captions, notes or coaching views from it. It is off by default: the twin’s administrator turns on Share voice transcripts with the embedding page, and the page asks for them when it loads the twin. Transcripts only ever go to the page hosting the twin.Full-screen avatar appears the moment it connects: Starting a voice conversation directly in the full-screen (immersive) avatar view could leave the avatar’s picture hidden behind the placeholder image even though the call was already live — it only appeared once you started speaking or pressed the mute button. The live avatar now shows the instant its video arrives, so an immersive call looks connected as soon as it is.Avatar greeting timing: The avatar’s introductory message now waits until its video, its audio, the session and the learner’s microphone are all ready (at most five seconds after the first frame), so the opening line no longer lands on top of the connection. A new Greeting delay (ms) setting beside the introductory message (default 1000) controls the pause before it speaks.Long-term Memory everywhere: Long-term memory is now managed the same way in both interfaces. In the classic interface, Manage Memory… (from the action menu’s Knowledge submenu) now opens with a Long-term Memory tab where you can browse, search, correct, forget and export everything your twin has stored — and choose whether it builds memories on its own or sticks to the facts you save by hand — beside the existing User Memory tab. In the new interface, the + menu’s Memory section gains the same one-click Enable Long-term Memory switch platform administrators already had in the classic Knowledge submenu (read-only for Digital Twin administrators). See Twin Memory.A reminder when files are waiting in your Trash: A small notice now appears above the + action menu whenever your personal vault has files in the Trash, so nothing is permanently deleted without you noticing. It tells you how many files are there and how soon the oldest will be purged, and one click opens the Trash so you can restore anything you still need. Administrators with file-edit rights on their Digital Twin see the twin’s Trash count too. Dismiss it and it stays quiet until something changes — a new file lands in the Trash, or a purge draws closer.Change how long a file is kept, right from the preview: The file-info panel beside the preview now shows a Keep if unused setting instead of a read-only date. Files that are still counting down let you pick a longer window or Forever on the spot, with the new “days left” reflected immediately. Files you have opened — previewing counts — or that Pria has used in a conversation are already kept for good, and the panel says so; files in the Trash show their purge date instead.File info on phones no longer squeezes the preview: On phones and small tablets, opening the file-info panel now slides it over the preview as a full-width sheet with its own Close button, instead of shrinking the document to a sliver beside it. The pin and enlarge controls stay where they were on larger screens.Select all in Files → Trash now selects every trashed file: Selecting all in the Trash tab was clearing the selection instead of selecting the files. It now selects every file in the Trash — including the ones not yet loaded — so Restore and Delete Permanently apply to all of them.Files you use are kept for good — and unused ones get 90 days: File longevity now works the way people expected it to. Your personal vault’s default is 90 days (up from 14), and a file only moves to the Trash if it has gone that long without ever being used — using it in a conversation, opening or previewing it, downloading it, or copying a share link all count. The first use is permanent: the file’s countdown ends and its “days left” badge disappears, and it never comes back even if you re-include or restore the file. Digital Twin vaults now keep files forever by default (0 days), so a twin’s knowledge base no longer thins out on its own. Uploading with a countdown shows an amber warning so you can pick a longer window or Forever on the spot. Existing files were brought in line: everyone’s 14-day default became 90, files still on the 14-day window gained the extra time, and every file that had already been used was set to forever — and files the old rule had moved to the Trash were restored.Memory row — see what your twin remembered and what it saved: Whenever an exchange touches your Digital Twin’s long-term memory, the answer now carries a single Memory row — the same expandable style as the Search Results row — listing every memory involved, each tagged with what happened to it: Recalled (brought back to shape the answer, with how it was found), Saved, Updated or Forgotten. Expand a memory to read what Pria remembered; a memory you marked as confidential asks for a second click before it is shown, and one you have since deleted says so. Administrators who prefer a quieter transcript can hide the recalled memories with the new Display Memory Details setting (on by default) in the Digital Twin’s Twin Memory section or in Instance Settings → Knowledge; memories keep working either way, and anything Pria saves, updates or forgets always stays visible. This replaces the earlier one-line memory badge.Turn on long-term memory from Instance Settings: The Knowledge tab of Instance Settings opens with a new Long-term Memory card so administrators can enable the feature and tune it without leaving the product — restrict it to admins while evaluating, choose the default memory mode for new conversations, share memories across the Digital Twins in your account, and control whether recalled memories appear in the Memory row. Enabling the feature itself and account-wide sharing remain platform-administrator actions and show as read-only for other admins. Platform administrators also get a one-click Enable Long-term Memory toggle in the + action menu’s Knowledge → Memory section, whose summary line now reports whether long-term memory is on for the current Digital Twin.Claude Fable 5.1 — Anthropic’s newest flagship model: Claude Fable 5.1 is now available on both the Anthropic API and Amazon Bedrock, for conversation, image analysis, summarization and the agent roles (conductor, planner, coder, tester, writer). It keeps Fable 5’s 1M-token context window and 128K-token responses, and its adaptive reasoning is always on — the model decides how much to think, and the Reasoning Effort setting steers depth from low to max. Prompt-cache reads are billed at 2.5% of the input price (versus 10% on other Claude models), so long, stable system prompts get markedly cheaper across a conversation. Like Fable 5 it carries the 30-day retention marker in the model selector. Select it in Admin → AI Models (the Bedrock variant requires the AWS account data-sharing opt-in plus a model-access agreement for this version; see the Platform Models guide).Prevent Personal Account Creation: A new instance setting lets administrators stop members from creating a personal Pria account for themselves. When it is on, the offer no longer appears for anyone working in that instance. Find it in your Digital Twin’s settings beside Prevent Switching to Other Instances. See Configuration.Jump straight to any setting in the admin panels: Editing a Digital Twin, account, or user on a wide screen now shows a quick-access list down the right of each tab. It names every section in that tab, highlights the one you are looking at as you scroll, and jumps to any of them in one click — so finding a setting no longer means scrolling a long form end to end. It appears only where there is more than one section to list, and only on larger screens.Guest twin links are easier to set up and cleaner to visit: The Convo Web Access Link — the public …/twins/your-name address anyone can open without an account — now sits with the other Convo settings in your Digital Twin’s Realtime / Convo section, and shows a scannable QR code beside the link for posters, badges, and screens. The visitor experience is tidier too: guests are no longer asked for their location, the page opens straight into the voice conversation instead of asking whether they want voice or text, and the duplicate close button that sat beside Logout is gone. See Guest Twin Links.Open an embedded twin with an assistant pre-selected (Web SDK): A new load option lets your embedding page open the Digital Twin in text mode with a chosen assistant already staged — the interface shows it as the pending choice, and the visitor’s own first message is routed to it. Nothing is sent on their behalf. Works on text-only twins (voice not required); if the visitor switches assistants themselves, their pick always wins. See the Web SDK guide.Twin Memory: Your Digital Twin can now remember what matters across conversations, and shows you a receipt each time it saves something — click it to see exactly what was kept. Review, correct, export or permanently delete anything it remembers in Settings → Memory. It is additional: your existing User Memory and Shared Memory are unchanged and keep working alongside it. Availability is set per Digital Twin by your administrator. See Twin Memory.Verified learner identity on external MCP tools: When your Digital Twin calls one of your MCP connectors, the request now carries a signed, server-verified identity for the signed-in learner. That means partner tools can safely answer personal questions — a learner’s own progress, quiz-result debriefs, tutoring observations — because the identity comes from the login session and can be independently verified by the partner’s server, rather than from text the AI generated (which a crafted prompt could fake). Admins will find the new MCP Signing Secret on the institution edit screen next to the existing MCP Secret, with copy and regenerate controls: share it with your integration partner through a secure channel, and coordinate before regenerating — rotation takes effect immediately. Existing integrations keep working unchanged; connectors that don’t verify identity simply ignore the extra information.The Agents workspace now fits your phone: The agents dashboard had been squeezing its chat into a sliver on small screens. The sidebar now collapses to a slim rail and expands the same way the conversations panel does — hover to peek on desktop, pin it open, or tap the edge handle on a phone — and it gets out of the way again once you pick an agent. The header reads Agents › agent name as a breadcrumb you can tap to reopen the agent list, replies use the full width of the screen, the message box sits centered beneath the conversation, and chat is now the landing view with Remote Desktop one tap away in the sidebar.Shared twin pages fill the whole screen on iPhone: Public twin links (guest access) no longer leave a colored band at the bottom of the screen on iPhones — the conversation now runs properly edge to edge in Safari and matches the twin’s light or dark theme while the browser’s toolbars come and go.Autonomous Agent settings moved: In the institution editor, the section formerly labeled “Agent” is now Autonomous Agent and sits directly below AI Behavior. The Realtime / Convo options were also regrouped: the kiosk-oriented toggles — Lock full-screen conversation and Start Immersive Mode by Default — each get their own row with their full descriptions visible.Avatar calls no longer fail when an assistant isn’t voice-enabled: Starting an avatar conversation with an assistant active in your chat used to end the call with an error if that assistant wasn’t enabled for Conversation Mode. The call now simply proceeds without the assistant (or with your institution’s default voice assistant, if one is set). To have an assistant participate in voice, an admin enables “Available in Realtime / Convo” on it.A dropped connection no longer cancels your Agent-Mode build: If your network blips, your laptop sleeps, or a proxy times out while an agent build is running, the work now continues on the server and the finished result is saved to the conversation — you’ll see it the next time you open that chat. Long-running builds are bounded by a server-side time limit, and an explicit Stop still cancels immediately. For API users: closing the streaming connection no longer cancels the request; use the documented abort endpoint to cancel explicitly.Cheaper Agent-Mode turns on Kimi models: The Kimi models that power coding and planning work in Agent Mode now pass Moonshot’s automatic prompt-caching savings through to you on every turn: input the model has already read is billed at a tenth of the full input price. Long multi-step build turns, where the model re-reads its accumulated context on every step, get the biggest reduction — the measured build turn cost roughly a third of its former price.Duplicate submissions are now caught: If the same question is accidentally sent again to a conversation while the first submission is still working (a double-click, a reflexive retry after a slow turn), Pria now recognizes it and points you back to the answer already in progress instead of starting a second run — and a second bill.Conversation Mode works from the new chat landing on every twin: The “Tap to start talking” button now starts Conversation Mode correctly on twins without an avatar — you’ll get the microphone permission prompt and go straight into the voice session.Quicker conversation renaming: Hover the conversation name at the top of your dialogue history to reveal a pencil and rename it in place. In the side tray, the conversation menu no longer overlaps the dialogue count.Cleaner pricing view: The Dialogue Report Card’s Pricing tab shows the itemized bill — every lane, model, tokens, and credits — while the explanation of how pricing is calculated now lives in the Plans & Credits guide, including the new Single-Shot and Subagent pricing sections.Keep a conversation in full screen (admins): A new Lock full-screen conversation setting in your Digital Twin’s Voice settings keeps people in the full-screen avatar view for the whole conversation. The collapse button and the Escape key are turned off, and ending the call is the only way out — so a learner in a kiosk or an embedded interview can’t accidentally land back in the chat interface mid-session. Starting, ending and muting the call work exactly as before, and the setting is off by default, so nothing changes unless you turn it on.Gemini 3.7 Flash available: Google’s newest Flash model (
gemini-3.7-flash) is now selectable everywhere Gemini 3.6 Flash is — conversation, image and video analysis, summaries, and the meeting/web assistant roles. Built for coding and multi-step agentic work, with the same 1M-token context window and introductory pricing at half the standard rate through the end of 2026.Grok 4.6 now available: xAI’s new flagship model, grok-4.6, can now be selected for Conversation, Image Analysis, and Summary. It keeps the 500K-token context window, image understanding, tool use, and pricing of Grok 4.5, and adds a deeper reasoning tier: setting your Digital Twin’s Reasoning Effort to “max” now unlocks the model’s highest thinking level instead of stopping at “high”. Prompt caching stays automatic, and long-context turns are billed at the standard rate until a prompt actually crosses 200K tokens.Text size controls now resize your conversation: The Smaller/Larger controls in the chat actions menu previously changed some interface elements but left the actual conversation text untouched — which made them feel broken. They now scale your messages, the reply text, and the typing area together, and Pria also respects the text size you’ve set in your browser’s own accessibility settings. Your choice is remembered between visits.Jump-to-latest is easier to find: The double-chevron that scrolls you to the latest message now floats just above the typing area instead of hiding at the bottom edge of the screen, at any input height.Google tools no longer disappear after saving instance settings: Fixed an issue where saving a Digital Twin’s settings — even for something unrelated — could silently switch off Google integrations (Gmail, Drive, Docs, Calendar) for every user of that twin. Affected twins have been restored, and the Google Workspace “Enable Access” toggle now correctly reflects whether the integration is active. If your assistant recently told you a Google tool was “disabled,” try again — reconnecting takes one Google sign-in prompt at most.Branded sign-in links now say when an account has no access: A branded login link (the “Convo Web Access” / invite URLs) paints the Digital Twin’s login page, but signing in with an account that was never given access used to silently drop you on your default assistant with no explanation — which read as “the twin disappeared”. Pria now tells you directly: a dialog names the twin from your link, shows which account you signed in with and where you actually landed, and offers Log Out & Switch Account so you can sign back in with the invited email address. Signing in with an account that has access — or as a platform administrator — now also switches you straight onto the branded twin.Persona mode is now standard: Persona mode has graduated from its experimental phase — the “(Experimental)” tag is gone from the twin settings, and newly created Digital Twins now start with persona mode on, so a new twin speaks as its character from the first conversation: capability and help questions are answered in its own voice, without platform guides or tool lists. Existing twins are untouched — whatever you have set today stays exactly as it is, and the toggle remains available either way.Lock an API key to specific sources (admins): A personal API key can now list exactly which sources are allowed to use it — server addresses (like 52.206.211.0/24 or a single IP) and/or web addresses (like https://app.example.com or *.example.com). Leave the list empty and nothing changes; your existing keys keep working exactly as before. Start with warning mode, where Pria records what would have been blocked so you can confirm the list is complete, then switch enforcement on. Keys are also easier to audit now: the “Recent device usage” list shows the actual tool that connected (for example curl 8.19.0 or node) instead of “Unknown client”.Pria no longer goes blank in privacy-hardened browsers or embedded views: On browsers that block site data or lack certain features — strict privacy settings, some mobile and LMS embedded views — opening Pria could show an empty page: the navigation bar, the admin console, voice mode, shared file and conversation links, and the sign-in redirect were all affected. Every one of these now loads normally; at most a cosmetic preference (like your dark-mode choice persisting between visits) is skipped. Text-to-speech controls likewise no longer break pages on browsers without a built-in speech engine. Behind the scenes, Pria also now reports these rare client-side errors automatically, so problems in the field get found and fixed without waiting for user reports.No more blank screens after an update: If part of the app fails to load — most often right after Pria is updated while you still have an older tab open — the page no longer goes blank. Pria now retries automatically behind the scenes, and if the content really can’t load it shows a clear “Pria has been updated” message with a Reload button instead of an empty screen. Nothing reloads without you choosing it.Digital Twin video no longer gets stuck on “Loading video…”: Launching a twin in Immersive mode could occasionally sit on the loading spinner forever, with stopping and restarting the twin as the only way out. The video connection now recovers on its own (it retries once automatically), and if it genuinely can’t start you get a clear “The video failed to load” message with a Restart button — plus connection errors are no longer hidden behind the auto-hiding controls in Immersive mode.Class Leaderboard (LXP): Every class now has its own leaderboard, next to the Syllabus and Gradebook — learners ranked by the points and skills they earned in that class only, not across the whole product. Open it from the class card menu on My Classes or from Analytics → Class Reports. Available in every language your site is translated into.Grades now reach your LMS gradebook reliably (LXP): When classes are taken through an LMS (Canvas, D2L and others), completed work now reports its grade the moment a student opens the assignment — previously, work finished outside that exact assignment session could silently never reach the LMS gradebook. Administrators also get a Resend grade button to push any learner’s current grade to the LMS on demand, with the LMS’s actual response shown so nothing fails silently.New in Analytics: LTI Grades (LXP): A product-scoped view of every grade exchanged with your LMS — search by learner, filter active vs completed records, hide records with no delivered grade, set how many rows to load, and export the filtered list to Excel. Administrators can resend any grade from the same screen.New in Analytics: Class Reports (LXP): One page listing every class in a product with the numbers that matter — learners, how many completed, average grade, who hasn’t started, inactive members, and last activity — with one-click access to each class’s Gradebook and Class Report.A clearer Analytics menu (LXP): The reporting menu is reorganized by what each page is about — Product, Skills, Classes, Journeys, Learners, and Integrations — instead of the old mixed groupings, and naming is now consistent: what were variously called courses or lessons are Skills everywhere. Menu labels remain customizable per customer, and existing translations are preserved.Sign in with Google lands you in the right place (LXP): Signing in with Google could open your account on the wrong customer/product context — class user lists, lesson lists, and admin pages then looked empty, and your profile picture disappeared. Google sign-in now lands on the same profile a password sign-in would (your most recently used one), with everything attached. If you saw empty lists after a Google sign-in, simply sign in again.Impersonate a learner straight from the user list (LXP): Administrators can now start impersonating someone directly from Manage Users — the row menu gains an Impersonate action, so there is no need to go to the profile screen first. It appears only on users you are permitted to impersonate, and asks for confirmation before switching, because signing in as someone else means logging in again to get back to your own account.Find the right person to impersonate without switching roles first (LXP): The impersonation screen gains a role selector, so administrators who manage several roles can search any of them without leaving the page, selecting a profile, and coming back. Choosing someone in another role now happens in a single step.Clearer profile cards (LXP): On the profile chooser, each card now shows Customer / Product so it is obvious which account a profile belongs to, and partner groups are listed alphabetically instead of in an internal order that looked random. Choosing a profile is now done with the Select button only — clicking anywhere on the card no longer switches profile, which removes the ambiguity with the card’s other controls. The delete control moved to the top-right corner as a clearly visible icon, where it no longer overlaps the buttons.Files can now expire automatically when unused: You can set a file longevity — how many days a file is kept without being used in a conversation before it moves to the Trash. Set your personal default on your profile, and (for Digital Twin admins) a separate default per twin under the twin’s settings; both default to 14 days, and 0 keeps files forever. Only files that are actually included in AI search count down, and every time Pria uses a file to answer a question its clock resets — so files you rely on stay put, and forgotten ones clean themselves up. Files show a small “days left” badge as they approach expiry, you can bulk-extend selected files (+7/+30/+90 days or keep forever) or set a specific file to forever from its preview, and expired files land in the Trash (restorable for 30 days) rather than disappearing. Every file already in your vault is unaffected — longevity only applies to files uploaded from now on.Deleted files now go to a Trash Can: Deleting a file — one at a time, in bulk, or by deleting a collection — no longer removes it immediately. It moves to a new Trash view in your Files vault, where it stays for 30 days and can be restored with one click. Restored files come back exactly as they were, including whether they were included in AI search. While in the Trash a file is hidden everywhere: it does not appear in your vault, in collection downloads, in the Knowledge Tree, and Pria will not use it to answer questions. After 30 days it is permanently deleted, and you can empty the Trash yourself at any time to reclaim space sooner.Deactivating a customer account now fully disables its Digital Twins: When a Praxis administrator marks a customer account inactive, every Digital Twin under that account immediately stops accepting new sign-ins and API activity across all channels — web, SDK embeds, LMS/LTI launches, MCP connections, avatar embeds, and content curation. Users who are members of other, still-active twins are guided to switch profiles rather than being signed out. Reactivating the account restores access within seconds, with no per-twin changes needed.AI-curated reading is live again, now powered by Pria (LXP): The recommended-articles carousel on courses and mission briefs stopped refreshing in December 2025 when the third-party service behind it was retired, leaving the same stale articles in place. Curation now runs on Pria’s own search, refreshed daily, and every suggested link is checked to be reachable before it is shown — no more dead links in the carousel. Existing articles were kept, so nothing you had disappears; new ones simply appear alongside them. Search terms are now stored in the LXP itself and can be edited per briefing under Manage Briefings, where previously they lived with the outside vendor and could not be reviewed. Where no terms have been set yet, they are suggested automatically from the course’s own skills and topics. To keep things current without wasted effort, only briefings attached to a course someone has opened in the last week are refreshed; a course that goes quiet keeps its existing articles and resumes refreshing as soon as a learner returns.Email delivery restored (LXP): Fixed a long-standing issue where system emails — password resets, activation links, enrollment notifications, instructor messages, and reminders — were not being delivered. If you requested a password reset in the past and no email arrived, it will work now.Expired lessons can now be un-expired (LXP): If a lesson showed Expired on a course that is not subscription-based, the Extend button silently did nothing — there was no subscription period to extend, and no way to clear the stale date. Extend now removes the expiry on courses that do not expire, so the lesson opens normally again, and the confirmation wording reflects what will actually happen instead of offering to “extend by 0 days”. Existing affected enrollments have been corrected, so anyone who hit this should find it resolved without doing anything.Bulk “Extend subscription” now updates the right enrollments (LXP): In Course admin, extending a subscription for several selected learners at once could write the new expiry date against unrelated enrollments while leaving the selected learners unchanged. It now updates exactly the chosen learners on the chosen course, and reports how many were updated and how many were skipped because they are not enrolled.Tidier archive for busy accounts on My Cohorts (LXP): If your archived cohorts span more than ten partner/program groups, the Archived section now opens as a compact index — every group heading and count visible, tiles tucked away until you expand a group with its checkbox. Searching still finds everything: while a search of three or more characters is active it looks inside collapsed (and unticked) groups too, revealing any match — the group checkboxes grey out to show search is temporarily in charge, and your expand/collapse choices return untouched when the search is cleared.My Progress page loads dramatically faster (LXP): Opening My Progress (competency scores and learning-resource statistics) previously re-computed data for every profile you hold, even though only the selected profile is shown. It now loads just the profile you’re viewing — on multi-profile accounts the page went from about five seconds to well under one.Find any cohort fast on My Cohorts (LXP): The My Cohorts page gains a search bar under the welcome message. Type three or more characters to filter your cohorts live by cohort name, partner, or program — no page reload — with checkboxes to include or exclude active and archived cohorts, a running match count, and a clear “no cohorts match” notice when nothing fits. Reordering tiles by drag-and-drop pauses while a filter is narrowing the list, so a hidden tile can never be shuffled out of place unseen.Archived cohorts grouped by partner and program (LXP): The Archived section of My Cohorts now groups your past cohorts under partner/program headings with a count per group, so it is obvious at a glance where each archived cohort belongs. Each group has its own checkbox to collapse or expand it, and the search filters inside groups too.Duplicate cohort tiles fixed (LXP): If you belonged to the same cohort through more than one enrollment, My Cohorts could show that cohort twice. Each cohort now appears exactly once.Archived cohort hover glitch fixed (LXP): In the Light and Space themes, hovering over an archived cohort made its outline vanish into the background. The outline now stays visible while hovering.Cleaner top bar on small screens: On phone-width windows the top navigation bar now hides the credits counter and the light/dark theme toggle so navigation buttons have room to breathe — especially alongside the Agent button on agent-enabled Digital Twins. Nothing is lost: “Add Credits” stays in the profile menu, joined by a new Theme entry that switches between light and dark mode at any screen size (it flips instantly and the menu stays open so you can see the change). The Agent Desktop button also now appears only while an agent-enabled Digital Twin is selected — it no longer shows on personal accounts.Kimi K3 available (RunPod): Moonshot AI’s flagship Kimi K3 (
kimi-k3) can now be selected as a conversation model, served through RunPod. It brings a 1M-token context window, native tool calling for agentic multi-turn work, and always-on reasoning. Add your RunPod API key to your Digital Twin to enable it.Integration wizard: Generate ready-to-use embed code for your Digital Twin without writing a line of it. Pick where the twin will run — Canvas LMS theme, a plain web page, a React app, or a Python-served site — configure the widget visually (position on screen, button size, full-screen, auto-open, start-in-Convo, and more, with a live preview), and copy or download the finished file. Visitor mode generates code that works instantly, giving each visitor a reusable guest identity that is cleaned up automatically when dormant; or switch it off to plug in your own sign-in. Find it under Instance Settings → Integration, or via the Integration button on the admin Instances list (which replaces the old per-row SDK copy buttons). The wizard also offers a Claude (LLM instructions) target — a drop-in CLAUDE.md that teaches Claude to drive your twin through the REST API and Swagger — and an Avatar widget target that generates the two-tag talking-avatar embed for any website (theme, launcher or inline mode, and microphone behaviour configurable; requires avatar embed to be enabled on the twin).Voice-first login — Start Immersive Mode by Default: Instance owners can launch visitors straight into the immersive voice conversation after sign-in — including one-click Google/GitHub/Facebook logins, SDK embeds, Canvas, and public twin pages. Turn it on in Instance Settings → Voice → “Start Immersive Mode by Default” (also in the admin instance editor). Visitors see a tap-to-start screen with the twin’s avatar (the tap is what grants microphone access — nothing is heard or billed before it) and can exit to the classic chat at any point; with the switch on, the next sign-in starts in the voice conversation again. Full-screen behaviour follows the existing Avatar Fullscreen setting. Digital Twins with a public guest page had it turned on automatically, so their visitors’ voice-first experience is unchanged.Resume-workspace errors no longer vanish: If resuming a sleeping Agent Desktop workspace failed, the error message could disappear immediately, leaving no indication of what went wrong. The message now stays visible so you can read it and retry.Gemini 3.6 Flash available: Google’s Gemini 3.6 Flash (gemini-3.6-flash) is now selectable everywhere Gemini 3.5 Flash is — conversation, image and video analysis, summaries, and the meeting/web assistant roles. Same intelligence tier with noticeably faster responses and lower output cost.Claude Opus 5 available: Anthropic’s new Claude Opus 5 can now be selected on both the Anthropic Direct API (claude-opus-5) and Amazon Bedrock (global.anthropic.claude-opus-5) for Conversation, Image Analysis, and Summary. Same price as Opus 4.8 with a 1M-token context window, 128K output, and reasoning that adapts automatically to the task. Note for Bedrock: your AWS account must have model access to Claude Opus 5 enabled in the Bedrock console before the Bedrock variant will respond.Mistral’s 2026 lineup added: Four new Mistral models are now selectable. mistral-small-2603 (Small 4) brings reasoning, image understanding, and tool use in one very affordable model with a 256K-token context window, for Conversation, Image Analysis, and Summary. devstral-2512 (Devstral 2) is a dedicated agentic-coding model, also with a 256K window. Audio transcription gains voxtral-mini-2602 (Transcribe 2) with improved accuracy at lower cost, and content moderation gains the updated mistral-moderation-2603.Grok 4.5 now available: xAI’s newest flagship model, grok-4.5, can now be selected for Conversation, Image Analysis, and Summary. It brings a 500K-token context window, image understanding, tool use, and adjustable Reasoning Effort — the first grok-4 family model where your Digital Twin’s effort setting (low/medium/high) is honoured rather than the model always thinking at full depth. Prompt caching is automatic and unusually effective on this model, so long conversations cost less per turn.Clear message when the AI returns nothing: On the rare occasion a model ends its turn without producing any text, Pria now shows a friendly “empty response — please try again” notice instead of an empty reply bubble. Applies across all AI providers.Collection downloads now require access: Downloading a collection as a ZIP now verifies you own the collection or hold file-access permissions on its instance. Previously the download link did not check membership.MCP server credentials no longer shown: Admin screens no longer display a configured MCP server’s stored authorization header. The interface indicates whether a credential is set; leaving the field empty on save keeps the existing credential unchanged.Agent Desktop now one click away for admins: Admins can open their Digital Twin’s Agent Desktop straight from a new button in the top navigation bar. The button appears for admins of Digital Twins that have Agent Mode enabled and leads to the desktop view with its connect and resume controls. Regular users are unaffected.Mute really mutes in immersive avatar conversations: Pressing the microphone mute button during a full-screen (immersive) avatar conversation now fully silences your microphone. Previously, with certain avatar voice configurations, sounds in the room could still be picked up while muted — interrupting the avatar mid-sentence or even triggering unintended responses. While muted, the avatar now finishes speaking uninterrupted and nothing you say is heard or answered; unmuting restores listening instantly.Documents with emoji no longer break conversations: Questions that drew on vault files rich in emoji or special symbols (for example, reports with emoji section headers or tables) could fail with a provider error — and once a file was affected, every question touching it failed the same way. Pria now handles emoji and special symbols safely, so these files just work. Existing files work immediately; there is no need to re-upload anything.Voice conversations recover cleanly from mid-turn errors: If an error occurred while a voice reply was already speaking, the turn could end abruptly with no explanation. Pria now ends that turn gracefully with a clear message instead of hanging.Consistent model management across every feature: admins now manage the models behind every Pria feature in one place — System → System Models (with per-Digital-Twin overrides where offered). Usage and billing always report the real provider that served each call, and your institution’s own provider keys (bring-your-own-key) are honoured throughout.Claude Sonnet 5 available across Anthropic, Bedrock, and OpenRouter: Claude Sonnet 5 can now be selected on Amazon Bedrock, OpenRouter, and the Anthropic API, with introductory pricing ($2/$10 per million tokens through August 31, 2026, then $3/$15). It is now the platform default model. Credit charges track actual provider costs more precisely, and Claude Sonnet 4.6’s maximum response length was doubled to 128K tokens.Turn User Memory on or off — one switch, your call: a new Enable User Memory switch (Your Profile → Knowledge → Memory — plus a quick toggle in the conversation action menu, on by default) gives you full control over personalization. Turned off, Pria stops saving new personal memories and stops using the ones it has — across text and voice conversations — while your existing entries are kept untouched and remain viewable, editable, and deletable in the Memory panel. Your team’s shared instance memory is not affected. See How Memory Handles Your Data for the full data-handling picture.Persona mode for Digital Twins: a new toggle (Instance Settings → Personalization, and the admin institution editor) keeps character twins fully in character. When on, questions like “what can you do?” or “where do I start?” are answered in the twin’s own voice, fully in character, and voice conversations use the twin’s personality throughout. Off by default; existing twins are unchanged until an admin turns it on.AI for Good Summit 2026 concierge — refreshed and sharper answers: Nova, the AI for Good Summit assistant (ai4good.praxislxp.com), has been fully refreshed ahead of the summit (7–10 July, Palexpo Geneva) with the latest official programme — 342 sessions, 1,231 speakers, 141 exhibitors, and 18 topic tracks. Answers also got more complete and better grounded: every speaker profile now includes their LinkedIn and social links and lists their sessions with the date, time, and room; exhibitor pages include contact and social links; and day-by-day and per-track answers are more reliable, so questions like “what’s on Thursday?” or “list all the AI for Health sessions” land on the right, complete answer.Bulk actions across more admin lists: The select-many toolbar now works beyond Users. Instances support bulk Set active / Set inactive / Delete, and Conversation history, Sessions, Assistants, Feedback, AI Models, Entitlements, and SSO providers each support bulk Delete. Tick rows (or Select all on screen), confirm the count, and they’re actioned in one step with a report of how many changed. Checkboxes respect your permissions — rows outside your institution are disabled — and the selection clears when you search or filter.Bulk-manage users — set active/inactive or delete many at once: The admin Users list now has a checkbox per row. Select users (or Select all on screen) and a toolbar appears with Set active / Set inactive / Delete and a count. Confirm before applying, and Pria updates them in one step, reporting how many changed and skipping any you can’t manage. Delete is a soft delete — accounts are deactivated and their email freed for reuse. The selection carries over as you scroll and clears when you search or filter.Two-step verification with an authenticator app — alongside email: Secure sign-in with an authenticator app (Google Authenticator, Authy, 1Password, or any compatible app), in addition to or instead of email codes. In your profile’s Two-step verification settings, choose Authenticator app, scan the QR code (or enter the setup key), enter a 6-digit code to turn it on, and save the 10 single-use backup codes (regenerate a fresh set anytime). Turn on email and the authenticator app together and manage each independently. At sign-in, Pria asks for your preferred method and lets you switch — “Send an email instead” or “Use a backup code” — right on the screen. An administrator can reset your authenticator if you’re locked out.Branded sign-in no longer carries over between users on a shared device: Logging out now fully clears the institution branding tied to your session, so the next person to sign in on the same device lands on the correct portal for their own account. Returning users who arrived through a branded link still see that brand on the sign-in page as before.Set guardrail instructions for your Digital Twin: Instance Settings (and the admin institution editor) now have an opt-in Guardrail instructions field with an on/off toggle. When enabled, your guardrail text applies across every conversation — chat and voice — for all assistants, without editing each one. Load default template fills it with an academic-integrity / Socratic rule (guide students’ thinking rather than complete graded work) that you can edit. It’s off and empty by default, and appears as its own Guardrail segment in the conversation’s context panel.Reasoning effort adapts to each model’s limits: Some advanced models (such as GPT-5.4 Pro) don’t accept the lowest Reasoning Effort settings. If your Digital Twin’s effort is set below the chosen model’s minimum, Pria now raises it for the turn instead of failing the request. Turning reasoning off entirely is still fully respected.Share your assistant with a public web link: Give any Digital Twin a short web address anyone can open — no sign-in needed. In Instance Settings → Invite → Guest Access, set a Convo Web Access Link (availability is checked as you type), then copy and share the generated link (for example
…/twins/your-name). Visitors land on a clean full-screen page that opens straight into a live voice conversation with your assistant, over your Digital Twin’s background, with a light/dark toggle. If voice isn’t available it falls back to text chat, so the page is never a dead end.See how much of your vault is actually being used: The Files Vault Health panel now has a Vault usage chart comparing how many files are in the vault, included in search, actually used (reached by a query), and processing or in error — each bar labelled with its count and share, with a headline percent of included files reached by queries. Each file card also gains a small usage dot — filled when the file has answered questions, hollow when included but never used — so you can spot unused files at a glance.More file types are now indexed: scripts, notebooks, calendars, and contacts: Uploading a shell script (.sh, .bash, .zsh, .csh), a Windows batch script (.bat, .cmd), an R script (.R/.r), a Jupyter notebook (.ipynb), a calendar (.ics/iCalendar), or a vCard contact (.vcf) now works — Pria reads and indexes their content for search instead of rejecting them as “not supported.” For a calendar, event titles, descriptions, and dates become searchable; notebooks are read cell by cell.Turn on the knowledge graph for your personal vault — no reload needed: When you enable the knowledge graph (KAG) for your personal files, the option now appears immediately everywhere it’s offered — including the Rebuild knowledge graph choice in the Reprocess dialog and your Vault Health panel — instead of only after a page refresh.Video scene analysis: Videos now get a visual description of what was shown on screen — not just the spoken words — so “what was shown” becomes searchable alongside the transcript. Admins choose the video-analysis model in System → System Models (a video-capable Gemini model by default) and can override it per Digital Twin under Institution → AI Models.Video and audio files transcribe reliably: Uploads that previously failed with connection resets or a “failed to parse audio file” error — common for .mp4 videos — now transcribe successfully, so their spoken content is captured for search. Silent videos (no audio track) are recognised up front and marked clearly (“File has no audio track.”) instead of failing with an opaque error.Tune search precision and detail per Digital Twin: Admins can set a Chunk Size for each Digital Twin under Institution → RAG and Files — Precise for sharp, fact-based answers, Balanced (the new default) for most content, or Broad to keep more context together — with a companion Chunk Overlap control. New defaults give more accurate answers at lower cost; existing files keep their current setting until reprocessed, and new uploads use the new setting automatically.Knowledge controls in Instance Settings: The Knowledge tab in Instance Settings now exposes two whole-Digital-Twin controls without opening the full admin Configuration page (admin access required). Ignore user personal vault — when on, the assistant answers only from the shared instance library and won’t draw on members’ personal uploads, for more consistent responses. The Chunk Size slider (above) is available here too.Edit a file’s details right in the Asset Info panel: A file’s title, filename, description, authors, dimensions (images), thumbnail, whether it’s included in search, and its visibility (private/public/confidential) are now editable directly in the Asset Info panel of the file preview. Click a field’s pencil to edit inline, flip a switch to include or exclude it from search, or click the thumbnail to change it — every change saves on the spot. You can also enlarge the Asset Info panel with the new double-chevron next to the pin.Edit a file’s text right in the preview: For text-based files — Markdown, HTML, plain text, and code — the preview now has an Edit content button that opens the whole file as editable text. Make changes inline and save, and the file is automatically re-indexed. (Binary files like PDFs and images aren’t editable this way.) A companion Edit Segments button still lets you fine-tune the individual passages the AI uses; open Properties to reach both editors.Editing a file segment now refreshes the knowledge graph too: When you edit or delete a file’s content segment, the change is now reflected in both search and the knowledge graph — previously only search updated.Track your background exports: Admins can now see every “Export all” job under System → Email Exports — its status (queued, running, done, or failed), the number of records in the finished CSV, who ran it and for which Digital Twin, when, and a link to re-download. Failed exports retry in one click, and a column selector lets you choose which columns to show (remembered).Instance Settings shows the correct tool on/off state: The Tools panel in Instance Settings now reliably reflects which tools are enabled or disabled for a Digital Twin, and toggling saves correctly. Previously some disabled tools could appear enabled.Export all — now on every admin table: The full-dataset “Export all” (prepared in the background, emailed as a private download link) is now available across all admin lists — Tools, AI Models, Saved States, Questions, session monitoring, Sessions, Payments, Entitlements, Feedback, Assistants, and Conversation history — in addition to Accounts, Users, and Institutions. Large exports now complete reliably no matter how many records match (a 179,000-row users export that previously failed now succeeds).Tree of Knowledge search finds everything: Searching the Tree of Knowledge now finds any entity by name — not just the handful shown in the default curated view — with a clear loading indicator while results stream in, instead of a premature “no matches.”Tree of Knowledge opens fast for large knowledge bases: Opening the Tree of Knowledge for a Digital Twin with a very large knowledge base — tens of thousands of entities — is now near-instant, where it previously took several seconds. Smaller vaults are unchanged.Reprocess into search and the knowledge graph — your choice: When reprocessing a file you can now tick Rebuild search index and/or Rebuild knowledge graph independently (tick both for a full rebuild). The same choice now applies to bulk reprocessing and to reprocessing an entire collection from its menu, so a whole collection can be rebuilt into the knowledge graph in one action. The knowledge-graph option appears only on Digital Twins that have it enabled.Move a sub-collection out of its parent: Nested collections now have a Move out of collection action that lifts the collection up one level — previously you could drag a collection into another but not back out.Export full datasets from admin tables: Admin list pages now have a CSV button with a dropdown — Export visible downloads the rows on screen instantly, while Export all extracts the entire filtered dataset. Large exports are prepared in the background; you’ll get an email with a private download link when ready (saved to your own vault, not shared). Available on the Accounts, Users, and Institutions lists, with System Models and usage views exporting as standard CSV.Search inside your files — with graph results and inline reading: The Files content search now includes knowledge-graph (KAG) matches wherever KAG is enabled for your personal vault or institution, not only keyword matches. Expand any result in place to read the full matched passage — and for graph-backed hits, see which knowledge-graph entities matched — without leaving the search panel.Users page tabs: The admin Users page now has tabs — Users, Statistics (per-user credit & usage stats, moved here from the History page), and Cap Effectiveness, a new view charting how the per-user 24-hour credit cap performs across instances. The Account, Institution, Account Type, and search filters apply to every tab.Admin list column controls: The Accounts, Institutions, and Users lists now have a Column Selector to show or hide optional fields — credit caps, model and voice configuration, KAG flags, last activity, per-user 24-hour usage, and more — remembered per admin. CSV exports now match the columns you have on screen. The Institutions list adds a per-user credit-cap indicator (Cap Tier, Per-user cap, Per-user 24h cap), and the History list gained optional metric and threat-status columns.Statistics tab — per-user credit-cap monitoring: The admin History → Statistics tab gains four optional columns — Effective Cap, Lifetime Used, % of Cap, and At Cap — surfacing each member’s credit-cap health alongside period usage. A summary line shows mean credits per user (by account and institution) and how many users are at their cap. The new columns are hidden by default; turn them on from the Column Selector.Instance user quotas — admins set per-user limits directly: Admins and managers with the institutions.edit entitlement can now set per-user credit quotas on their Digital Twin — a per-user lifetime cap and a per-user rolling 24-hour cap (the 24-hour cap recovers automatically as recent usage ages out). Set them in the new Quotas tab in Instance Settings or the Credit section of the admin Configuration panel. When the parent Account has caps enabled, the instance inherits them read-only; otherwise it self-configures. Leave a cap blank (or 0) for no limit. See the Credit Allocation & Transfers guide.Usage chart — see how many users were active: Institution admins viewing usage for all users of a Digital Twin (Pricing → Usage) now also see how many distinct users were active in each period, drawn as an amber line over the credits chart with its own axis, matching your chosen bucket size (daily, weekly, or monthly). The running total gains a true distinct-user count for the whole window. Your personal usage view is unchanged.Credit usage caps: Operators can now set per-user credit limits on an account — a lifetime account-wide cap, a per-instance cap (with overrides), and a rolling 24-hour cap. When a user reaches a cap they’re blocked from spending more until it’s raised (or, for the 24-hour cap, until recent usage ages out). Users see a small usage gauge in their gallery and a clear notice when they hit a limit; admins can review usage-versus-cap and how many members are at a limit. Caps are off by default.See your credit usage over time: The Pricing page has a new Usage tab charting the credits you’ve spent per day, week, or month for the selected Digital Twin (or your personal account). Pick a window (7 to 180 days) and bucket size, and the bar chart shows spend per bucket with a running total of credits and messages. Institution admins get a checkbox to switch between your own and all users’ usage for that Digital Twin (hidden for personal accounts). Reading the chart is free.Persona Builder — a guided onboarding interview for every Digital Twin: Personalizing a Digital Twin now runs through one curated 14-question interview — the Persona Builder — grouped into five sections (Basic Identity, Role and Primary Use Case, Audience, Communication Style, Advice Style and Guardrails), identical on the admin onboarding tab and in the create-a-twin wizard. It uses richer question types: selectable tiles for single-choice questions and a personality slider group (a 1-to-7 scale for each of seven traits: tone, energy, detail, feedback, humor, thinking, warmth). Every answer feeds the twin’s Instructions via Generate Prompt. Required questions must be answered to continue; the email question prefills from your account (and never changes your login), and the twin-name question stays in sync with the instance name. See the Onboarding Questions guide.Onboarding popup now skips already-personalized twins: The first-time prompt to run the Persona Builder no longer appears for Digital Twins that already have Instructions. It still shows for un-personalized twins and continues to yield to the Canvas sign-in prompt where that applies.Read responses aloud with a natural voice: Pressing Speak on a response can now play it with a natural-sounding voice from your Digital Twin’s text-to-speech model instead of the basic browser voice. Institution admins turn it on per Digital Twin in Instance Settings → Voice → Natural Voice and pick the read-aloud voice there; personal accounts get a Use Natural Voice toggle in Your Profile → Conversation Preferences with a Playback voice picker. The chat’s [+] → Audio menu shows the current state and jumps to the right settings. Every voice picker has a Preview button that plays a short sample (previews are free). Generating audio consumes credits based on response length; replaying the same response is free.Claude Fable 5 — Anthropic’s newest flagship model: Claude Fable 5 is now available as a conversation, image-analysis, and summarization model, on both the Anthropic API and Amazon Bedrock. It brings always-on adaptive reasoning, a 1M-token context window, and 128K-token responses. Select it in Admin → AI Models (claude-fable-5 on Anthropic, global.anthropic.claude-fable-5 on Bedrock — the Bedrock variant requires an AWS account data-sharing opt-in; see the AI Models guide).Zero Data Retention — clear compliance signals in the model selector: Praxis AI ships only models that comply with Zero Data Retention (ZDR) — your prompts and responses aren’t stored by the model provider — and the model selector now says so. The one exception is clearly flagged: Anthropic’s Mythos-class Claude Fable 5 carries a red warning and a “30-day retention” marker, because Anthropic retains prompts and outputs for these models for 30 days (effective June 9, 2026). The warning links to Anthropic’s retention notice, and the AI Models guide has a new ZDR section.Lower AI costs — smarter prompt caching across every provider: Repeated conversation turns now cost less across all six AI providers (Anthropic, Bedrock, OpenAI, Google, Mistral, and xAI), with the savings passed on as larger credit discounts. The dialogue info card shows cache activity per response, and a new copy button lets you copy all its metrics as JSON. In Conversation (voice) mode you can also tap the new full-screen (TV) button to put the assistant’s avatar front and center, filling the entire screen — great for presentations, kiosks, and hands-free use. It works from the compact widget and the expanded view, goes true full-screen on desktop and Android (fills the screen on iPhone/iPad), and you can exit any time with the on-screen button or the Esc key.Praxis Shield — threat monitoring for your Digital Twins: Institution administrators get a new Threats panel. Conversations are scanned automatically in the background, and potentially abusive or concerning activity surfaces as incidents with a severity, status, and categories, plus a detail report of the relevant conversation context. A built-in triage workflow lets reviewers add notes, progress status, and see the full action history; confirmed abuse can suspend the user’s membership in that Digital Twin (reversible any time), and harmless flags can be marked false positive. Filter incidents by account, Digital Twin, status, or minimum severity. Scanning is invisible to end users and never blocks or alters their experience. See the new Praxis Shield admin guide.Praxis Shield — shareable incident reports: Every incident has a read-only report you can share by link with another administrator of the same Digital Twin. Reports are login-gated and only open for admins who manage that institution, so sensitive context stays in the right circle.Admin console — cleaner navigation on large screens: The admin menu can now collapse into a slim icon-only rail (your preference is remembered), and multi-tab dashboards share a unified layout where the tab bar becomes a collapsible left sidebar and only the content panel scrolls — so headers and navigation stay in view while you work through long lists.Embed your Twin’s talking avatar on any website: A new Avatar Embed Widget puts your Digital Twin’s voice-enabled avatar on an external site with a single script tag (or a React component). Choose a floating launcher or an inline embed, light or dark theme — visitors talk to your Twin without leaving your page, and only a public embed key is required. See the Avatar Embed Widget guide.Admin — run background AI jobs on cost-effective Bedrock models: Background AI jobs (knowledge-graph extraction, threat detection, and summarization) can now use low-cost open-source GPT models on Amazon Bedrock (gpt-oss-120b, gpt-oss-20b, and the safety-tuned gpt-oss-safeguard pair). Several inexpensive models (Amazon Nova micro/lite/pro, Gemini Flash-Lite, and others) are now also selectable for summarization, giving you a price/quality ladder. Each model shows its price per million tokens and capability badges (structured-output, code, vision, reasoning) so the trade-offs are clear at a glance.Admin — see credits consumed per member, per instance: Each membership now tracks the lifetime total of pooled credits that member has drawn from the instance, shown as a Credit Consumed column in Admin → Users → Membership and on the Entitlements list (and in the Entitlements CSV export). It complements credits awarded — handy for usage reporting and spotting unusual consumption. It applies to instances that pool credits across members; personal accounts are unaffected. On the Membership tab it replaces the rarely-used Award Date / Award Amount columns.Admin — merge two user accounts into one: Admins can consolidate a duplicate or vanity-email account into another (for example folding an old personal-email login onto a member’s work account). From the Users list, the new Merge into… action lets you pick the surviving account, see a preview of exactly what will move (and any overlaps or billing caveats), then type the source email to confirm. On confirm, Pria moves all of the source’s content, history, and memberships to the target, sums their credits, removes the source’s logins, and permanently deletes the source — recorded in an audit log. Requires both edit and delete permission on the users involved.Admin Conversation History — show or hide user-deleted conversations: The admin History list now hides conversations a learner removed from their own history by default, with a Show user-deleted toggle to bring them back when needed. Revealed records carry a small deleted badge. A learner’s delete is still respected everywhere it was before — this only changes what an admin can optionally surface.Conversation exports & history — assistant replies no longer appear blank: Downloaded conversation data (including the GDPR-style data export) and the admin history detail view now show the full assistant reply text, fixing cases where streamed replies previously appeared empty.Privacy — stronger isolation of personal files and memory: One member can never read, list, or modify another member’s personal-vault or confidential files, and can’t overwrite or clear another member’s or the organization’s shared memory — those stay owner- and admin-managed. Genuinely shared (instance) files still work across an organization as before. The unused “list all members’ files” option was removed.New AI model — Grok Build 0.1 for coding: xAI’s Grok Build 0.1, purpose-built for agentic coding (web development, debugging, and multi-step build tasks), is now selectable as a conversation model. It’s fast and cost-effective, reads images such as diagrams and screenshots alongside your code, and always reasons through a problem before answering. Admins pick it as a Digital Twin’s conversation model in Instance Settings → AI Models.Files — mark a whole collection confidential in one click: A collection’s ⋯ menu now has Make All Confidential and Remove Confidential alongside Make All Public / Make All Private. Making a collection confidential lets Pria keep using those files to answer but stops it from citing them — applied to every file in the collection and its sub-collections at once. (Confidential and public are mutually exclusive, so this also removes public access.) Remove Confidential reverses it so those files can be cited again.Personal knowledge graph — now available to everyone (opt-in): You can now build a knowledge graph from your personal files. A new Build a knowledge graph from my files toggle in Your Profile → Conversation lets any user opt in, so search can connect related ideas across your documents rather than just match keywords, and your chat Knowledge → Sources menu gains the RAG + KAG Fusion option (shown when a knowledge graph is available on your personal vault or current Digital Twin). Files shared through an organization keep using that organization’s own setting. Turning the toggle off keeps any graph already built, so re-enabling is free.Personal knowledge graph — process the files you already have: New uploads are added to your knowledge graph automatically once you opt in. For files uploaded before enabling it, a panel under the toggle shows how many aren’t in your knowledge graph yet and an Add my existing files button to process them, with a live progress bar and a Stop control. Files you add next always take priority, so turning this on never slows new uploads.File Preview — knowledge-graph usage itemized per file: Each file now tracks its knowledge-graph processing cost separately from standard search-indexing, so the File Preview shows what each step cost for that file.Admin — KAG Fusion is now a self-service setting (no longer Praxis-managed): Knowledge-graph fusion can be configured directly in the admin console instead of requesting it from the Praxis team. Accounts gain a Knowledge Graph (KAG / RRF Fusion) section with two cascading controls — Enable KAG for all instances and Allow instance-level KAG toggles (the first takes precedence). Instance Settings → Ingestion has an Enable KAG Fusion for your Digital Twin toggle that any admin with instance edit rights can use, and it shows when the setting is inherited from the account. Admins can also set a specific user’s personal-vault KAG from Admin → Users → Knowledge. Each surface links to a More info on KAG reference and notes that building the graph improves answers on complex questions but uses more credits than plain embedding.Admin — process a Digital Twin’s existing files into its knowledge graph: Like the personal-vault control, Instance Settings → Ingestion now shows — once KAG Fusion is on for the Twin — how many of that Twin’s files aren’t in its knowledge graph yet, with an Add existing files button, a live progress bar, and a Stop control. Any admin with edit rights on the Digital Twin can run it.Files — knowledge-graph coverage in Vault Health: The Files modal’s Vault Health panel now has a Knowledge Graph (KAG) section that tells you whether all eligible files are in the knowledge graph and, when some aren’t, gives an Add existing files button with a live progress bar and Stop to backfill them right there. On your personal vault, if KAG isn’t on yet, it offers an Enable for my personal vault button that switches it on and starts processing in one click. It appears for the Personal and Digital-Twin vaults, and is hidden in the combined All-Vaults view.Tree of Knowledge — available to everyone with a knowledge graph: The Files → Tree display toggle — a visual map of your knowledge graph (pillars, entities, relationships, and the source files behind them) — is now available to anyone with a knowledge graph. You can switch between Files and Tree: users who belong to a Digital Twin, or who’ve enabled KAG on their personal vault. The vault picker inside the Tree only offers vaults you can reach, and the tree only shows knowledge built from files you can already access.Admin — Accounts page polish: The General tab is grouped into clear sections (Account, Managers & Domains, Knowledge Graph, Privacy Policy); the Privacy Policy Consent Form is now a Markdown editor with a live Preview; the number of linked instances shows on the Instances tab (e.g. Instances (18)); and the unused Qualification field was removed.Image generation — request larger or differently-shaped images: When you ask Pria to create an image, you can now request a specific size or shape — a wide landscape, a tall portrait, an aspect ratio like 16:9 or 9:16, or a higher resolution where the selected image model supports it. The default is still square, and if you ask for a size a model can’t produce, Pria uses the closest available size instead of failing.Image generation — faithfully enlarge an existing image: You can now ask Pria to upscale an image you already have (for example “enlarge this 2x”), increasing the resolution while keeping the picture exactly as it is — same composition, colors, and detail. This works with any configured image model. (It’s a clean enlargement, not AI “enhancement,” so it won’t invent new detail.)Backgrounds — set them from a picture or your webcam: The light- and dark-mode background images can now be set like a profile picture — click the background thumbnail to upload a file or capture from your webcam, crop it to a wide 16:9 frame, and save. It’s available in Instance Settings → Personalization → Appearance and, when editing an organization, on every picture in the Personalization tab. Webcam capture requests HD so backgrounds stay crisp, and you can still paste an image URL directly.Conversation History — see what was retrieved during each turn: Every history record now shows a RAG Search Results panel — alongside Thinking Details and Tool Details — listing the file segments Pria pulled in for each turn (file name, relevance %, and a preview of the text). It appears in the chat list, the public history viewer, and the admin History inspector. Confidential segments owned by another user in your institution show a 🔒 with the preview redacted. History pages stay fast — the full detail loads only when you expand a section.Conversation History — unified detail panels with per-entry copy: The Thinking, RAG, and Tool detail panels now share one consistent look everywhere they appear (chat list, single-record viewers, admin inspector), and each entry has a copy-to-clipboard button so you can grab a reasoning round, a retrieved chunk, or a tool response in one click. Tool Details now loads full arguments and responses the moment you open it — no more follow-up click. Live streaming Thinking matches the saved view.File Preview — Processing timeline for RAG and KAG: The Asset Info → Processing section of the File Preview modal now splits into two color-banded blocks — 🔵 RAG · embeddings and 🟣 KAG · knowledge graph — each with a step-by-step timeline (Enqueued → Started → Completed) showing durations and timestamps, a ✓ on finished steps, a pulse on the step in progress, and a red ✗ if a run failed. Each model row shows a provider chip (e.g.
text-embedding-3-small [openai]) so admins can see which model handled the file. A combined Total tokens and Cumulative time pair appears when both phases have run, with per-phase figures in parentheses. The Properties Uploader row was renamed Owner to match the rest of the platform.File Preview — live KAG progress: While a knowledge-graph job is running, the Processing > KAG block now shows a Progress: N% row and the current step inside the timeline. The same live step appears for RAG while a file is being processed; once finished, the completed step is the only signal needed.Hide live Thinking / Tool indicators without losing the audit trail: Two new toggles in Your Profile → Conversation (and on the admin instance edit page) let admins hide the live streaming surfaces on their own. Display Thinking Execution controls the 💡 reasoning block shown in real time; Display Tool Execution controls the inline ⚙️ Running… / 🔧 Ran ✓ indicators. Turning either off keeps the live conversation clean while the separate Display Thinking Details / Display Tools Details toggles still control what’s saved to History. Both default to on.File Preview — redesigned segment editor: Entering Edit mode now hides the Asset Info sidebar so the segments editor uses the full modal width, with Title, Summary, Rights, and segments in one clean top-to-bottom form under File Properties / RAG Segments headers. A new Rights group lets admins set a file Private / Public and, for instance or account vaults, flip a Confidential switch (locks it for other members) — each saves immediately and the file-grid badges stay in sync. + Add Segment is now a full-width button after the last segment, and each segment has its own Update action (saving just that one) next to Sanitize / Delete. Typing into a segment now reliably persists. On narrow screens the segment header collapses to icons and a compact character counter so it stays on one row. The unused Tags / AI Tags rows were removed.Voice dictation — mic stays available after transcription: The mic button no longer disappears once your dictated text lands in the input. Click it again to add more — each new dictation is appended (with a separating space) so you can build a longer message in several passes. After a transcript comes back, the caret jumps to the end so you can keep typing or hit Enter right away.Files — Properties and Edit Segments merged into File Preview: The old separate Properties and Edit Segments dialogs are now one File Preview window, so you no longer switch screens to view metadata and edit search segments. A collapsible Asset Info sidebar groups Properties / Processing / Knowledge — RAG segments, pinning open or expanding on hover like the Pria and Files-search sidebars. The Edit Segments action opens the preview directly in edit mode; Title and Description gain inline pencil edits. Copy file name and Copy link buttons sit next to Download, and fullscreen now expands the whole window. Action dialogs (Reprocess, Swap Asset, Delete) reliably layer on top.Files — Swap Asset (replace a file without rebuilding its index): A new Swap Asset action in the file’s ⋮ menu replaces the underlying file while keeping its existing knowledge (embeddings, summary, title) and its published URL — so anything already linking to the file keeps working. Useful when the source file was lost but the indexed content is still good, or to refresh the downloadable copy. Supply a new file or a URL for Pria to fetch. If you want the new content searchable, run Reprocess Content afterward. The action is hidden when a file is missing from disk with no embeddings (Delete is the only option there).Files — Vault Health pills are now the filter: The Vault Health pills at the top of the panel (needs reprocess, errors, needs delete, missing, unoptimized, stale >90d, never used) now act as filters — click one to scope the listing to that category, click again to clear. The Vault Summary shows a single Health: <grade> chip (A–F) that jumps to the Vault Health section. A new needs delete category flags files missing on disk with no embeddings, where Delete is the only valid action.Files — sidebar polish, lightbox maximize, RAG tuning, Tree of Knowledge: A second pass on the Files modal. The sidebar is now a pinnable rail (pin to keep open, or hover to expand). Search became a Search Type control (File Name / AI Content) with a multi-line box and a dedicated Search button — typing no longer auto-fires, and a clear-X resets the query. A new All Vaults checkbox searches your full scope; both preferences persist. Content-search results show a “found in” chip with the vault and collection; clicking a hit jumps straight there. Admins with edit rights get inline RAG Tuning sliders (Search Affinity %, Max Articles) that re-run the search on save. Tree of Knowledge is promoted to a top-level Display selector (Files vs Tree). The Lightbox gained a Maximize / Restore toggle and goes full-bleed on narrow screens. File status pills were replaced by a small icon strip (Included / Public / Confidential), and resizing the file list is noticeably smoother.Files — content search across your IP Vault: The Search box gained a name/content toggle. In content mode, press Enter to search across the same files your assistants use (your personal vault, current institution, and account-shared files) and get a scored-snippet results panel. Each card shows the file name, a relevance badge, and a highlighted 200-character snippet; confidential files owned by another member show a row and score but no snippet (🔒 Private content matched — open the file to view). Clicking a result selects the file and snaps to it. A ”← Back to N search results” banner lets you flip back without re-running. Limited to 20 searches per minute.Files — responsive sidebar on large screens: On screens ≥1024px, the Search / Display / Sort controls now stack in a 240px left rail beside the file grid instead of a toolbar above it, with Add Files pinned to the bottom. Smaller screens keep the horizontal toolbar. The Display, Sort, and search-mode controls all adopted the same look as the View Mode switcher, with proper screen-reader labelling.Knowledge picker — clearer Retrieval Mode + Search Only: The Knowledge submenu (in the [+] menu and the Knowledge tab of Your Profile) is reorganised into a three-option Retrieval Mode — Disabled, RAG Only, RAG + KAG Fusion — plus a separate Search Only checkbox you can combine with either mode to return raw vault results without an AI rewrite. The old “KAG Only” label was misleading (KAG always augments RAG), so the new copy makes the relationship clear. The Knowledge row badge reflects the active state — Disabled (red), Search Only (amber), RAG + KAG (blue). Existing profiles carry over with no migration. The glossary gained KAG and Knowledge Modes entries.Voice dictation — in-place recorder with live waveform: Tapping the mic in the chat input now opens a dictation widget right where the textarea was — a pulsing red dot, an MM:SS timer, a live waveform, and Cancel / Confirm buttons. Recording stops automatically at 2 minutes (with a 10-second warning). It uses your institution’s configured speech-to-text engine (Voxtral / Whisper / etc.) rather than the browser’s, so accuracy and language coverage match the rest of the platform. Nothing is stored after transcription — no upload, no history, no embeddings. Works in Chrome / Firefox / Edge / Safari. On Confirm, the text is appended to whatever you’ve already typed.Your Data Rights (GDPR controls): A new Your Data Rights section at the bottom of My Profile → Your Data lets you see, export, and delete the personal data Pria holds about you. A stats card shows your personal dialogues, vault files (with total size), and memory entries. Export my data builds a ZIP (README, dialogues.csv, uploads.csv, memory.csv, plus your original upload files) and emails you a signed download link valid for 30 days. Delete my data opens a confirmation where you choose to forget your Dialogues, your Personal files in Vault, or both. Everything is scoped to your personal data — institution and account data is governed by the institution’s own retention policy and untouched. Exports are limited to one per hour, and emailed ZIPs are purged after 30 days.Files panel — full redesign: A top-to-bottom polish of the IP Vault Files modal — Google-Drive-style cards, a horizontal collections strip above the grid (drag a file onto a folder to move it), a redesigned File Preview with an Asset Info sidebar and lazy-loaded RAG content, and a Grid / List / Table view switcher. The Lightbox scales to the full viewport on wide screens. A new Vault Health header shows an A–F grade plus an attention dot for the most pressing follow-up, and a new “Needs reprocess” category flags files that are Included but have no embeddings (common after an embedding-model switch). The bulk action bar is now sticky. Drag files onto a vault tab (My Files / Instance / Account) to move them between vaults. The new table view (Files and Assistants) supports client-side sort, infinite scroll, bulk select, resizable columns, and a Columns menu (Source, RAG Hits, Last Used, Owner, etc.) that persists per user. The Properties dialog was rearranged into clean per-section cards.Collections — custom colors: When creating or editing a collection (or sub-collection) you can now pick an accent color from ten swatches or any custom hex. The folder icon renders as a solid tinted shape across the strip, list, and card views. Pick the ∅ option to revert to the default outline icon.gpt-realtime-2 is now the default voice model: OpenAI’s newest realtime voice model replaces gpt-realtime-1.5 as Pria’s default for Convo / Speech-to-Speech mode. It brings GPT-5-class reasoning with configurable reasoning effort, a 128k context window (4× the previous default), stronger instruction following, and translation across 70+ languages. Reasoning tokens per turn are now tracked separately as Thinking Tokens in the usage card. Earlier models (gpt-realtime-1.5, gpt-realtime, gpt-realtime-mini) remain in the picker. Note: gpt-realtime-2 audio pricing is materially higher than -1.5 — review your Pricing tab if you run at scale. Institutions that had explicitly chosen -1.5 stay on it; only those without a chosen model move to the new default.OpenAI Realtime endpoint migration (GA): OpenAI realtime voice sessions now use OpenAI’s GA endpoints instead of the deprecated beta ones. The change is transparent to end users — same voice, VAD, and tools — but network admins should ensure outbound HTTPS to api.openai.com/v1/realtime/client_secrets and api.openai.com/v1/realtime/calls is allowed; the legacy /v1/realtime/sessions path is no longer used.Voice agent now sees account-shared files: When you ask the voice agent “how many files do I have?”, it now includes files shared across your organization (the Account vault), not just your personal and institution files. These files are labeled Owner: Account so you can tell them apart in tool-call traces. Previously they were silently missed even though the file modal showed them.Live transcripts during voice sessions: The character-by-character transcript under the voice indicator now works for OpenAI realtime sessions (previously it showed only the final transcript at the end of each turn). Your own speech also appears live as You: … as soon as it’s transcribed.Thinking Tokens — visible in every history surface: Reasoning-model output is now reported separately from the visible answer. Everywhere token counts appear — the inline usage card, the per-message info card, My Profile → History, and the Admin → Histories detail modal and table — a new Thinking value shows when the conversation used a reasoning model. OpenAI (Chat Completions, Responses, and Realtime GA) and Google Gemini report this; Anthropic / Bedrock / Mistral / xAI don’t yet expose a separate count, so it stays 0 for those. Thinking text blocks are still saved as before.Google Cloud — revoke before changing services: Both the personal Google Cloud panel (My Profile → Google Cloud) and the institution Google Workspace integration (Admin → Instance → Configuration → Google) now lock the service toggles while a token is active. To add or remove Gmail / Drive / Calendar, click Revoke Access (or Disconnect) first, then re-authorize with the new selection. An expired personal token shows a Re-authorize Services button. A short hint explains the flow so the disabled state isn’t ambiguous.Welcome / Canvas-auth popups dismiss reliably: The “Welcome to your new AI Digital Twin!” prompt and the Canvas-auth recommendation popup now close as expected when you click Later, Yes, Enable, or Dismiss, instead of occasionally lingering after saving.User Guide & Admin Guide open in a new tab: Clicking User Guide or Admin Guide (from the [+] menu under More, or the sidebar buttons) now opens the documentation site at docs.praxis-ai.com in a new browser tab instead of an embedded panel that rendered empty.Logout — branded login page preserved: When you reach Pria through a branded URL and log out, the post-logout login page now keeps your brand assets instead of falling back to the default Pria look.Logout — cross-session state leak fixed: Logging out and signing in as a different user no longer surfaces the previous user’s Digital Twins in the top-navigation switcher. Entitlements, user-institutions, and in-flight requests are now cleared on every logout, and stale requests fired during logout no longer surface as 403 console errors.Instance Settings — Voice tab, explainers, and polish: The instance-settings lightbox gained a dedicated Voice tab (between Personalization and Conversation) with the Convo / Speech-to-Speech model picker, per-provider voice selectors (Gemini Live, xAI, OpenAI Realtime — voice, VAD eagerness, noise reduction, transcription language), and a shortcut to the full admin models page. Retrieval is now called Knowledge and opens with a collapsible explainer covering IP Vault security, RAG, and KAG Fusion; matching About tools and About assistants explainers were added. The Conversation > Behavior card gained Enable Moderation and Cite Sources toggles; Tools Guidance and a new Max Tool Result Size (default raised to 60,000 chars) moved to a Tools tab card. Personalization gained an Enable Location toggle and richer descriptions. The Billing tab hides Add Credits when Disable Add Credits is set, the Invite tab gained a Manage Members & Entitlements shortcut, and the Identity tab was renamed General.Personal Settings — descriptions + Knowledge Sources cues: Each Personalization and Security toggle now carries a short description (Dark Mode, Use Location, Enable STT, Knowledge Sources, Must Change Password, Reset password on SSO Login). The Personalization tab shows the current retrieval state at a glance — an amber dot for Search Only, a red dot when Knowledge Sources are disabled. The Google Cloud entry shows a green “Connected” dot when your personal Google token is valid or the instance has Google OAuth enabled.Action menu polish: Item labels are now consistent Title Case — Audio Notes is New Audio Note, Create new assistant… is New Assistant…, List Assistants is Manage. The Knowledge Sources submenu’s active dot uses the same tones as the Personalization tab (amber for Search Only, red for Disabled). The Switch assistant for next message picker is now a clean filtered list that keeps the current assistant with a “Current” pill so you can clear an override in one click. The next-assistant chip sits to the left of the send button.Instance Settings — Invite & Billing tabs, plus Conversation toggles: The instance-settings lightbox gained two tabs. Invite generates a join QR code and copy-to-clipboard invite link for new members, plus a branded login link for existing ones. Billing shows the instance credit balance with an Add Credits button (to the Pricing page’s credit tab), a note on pooled vs. non-pooled credits, and a payment-history table for this twin. The Conversation → Behavior card added Enable Moderation and Cite Sources toggles, and Tool / Assistant rows now show their description under the name.Profile & Instance Settings refresh: Both surfaces were reorganized. In My Profile, Profile is now General, Preferences is Personalization (with the Dark Mode toggle and a new Appearance card), and a new Billing tab shows your personal credit balance, an Add Credits button (to the Pricing credits tab), a payment-history table, and a note explaining when personal credits are used. In Instance Settings, the Features tab is now Personalization and carries a new UI Theme selector (User Directed / Dark / Light), the Display Thinking Details / Display Tools Details toggles, and the Guest UI toggle alongside the file-upload / audio-notes / clipboard toggles.Dialog Usage Details — in-place card: Each message header now shows a bar-chart icon on hover next to the timestamp. Clicking it swaps the message body for a color-coded usage card with the model name, a provider chip, full timestamp, token counts (total / input / completion / baseline), cache discount, credits, retrieval timing, tool names and count, thinking-block count, latency, and request duration. Click again to return to the message. This card is now visible to every user (previously admin-only), and all row colors meet WCAG AA contrast in light and dark mode.Memory Panel — filter by instance: When your memory spans more than one digital twin, My Profile → Memory now shows a searchable instance picker beside the namespace and scope filters. Each option shows the institution’s logo, ainame, and display name, with a “Personal” bucket for entries not tied to an instance. It defaults to your current instance and stays hidden when your memory lives in a single instance.Push-to-toggle microphone: The dictation mic now stays on until you click it again. Previously it stopped after a short pause and needed a fresh click for the next phrase. Now one click keeps it running through pauses and silences, and phrases accumulate in the input as you go — it stops only when you click it off or submit.Admin Histories — column selector + User Statistics tab: Two upgrades to Admin → Histories. (1) The Records and Usage tables each have a Columns dropdown — toggle any column off to declutter, saved per-admin and dropped from the CSV export too. (2) A new User Statistics tab shows one row per user per day / week / month with query count and credits used, respecting your toolbar filters. Toggle the period and click CSV for a per-user usage extract. Results cap at 5,000 rows with an amber banner when truncated.Gemini 3.1 Flash Lite is now GA: Google promoted gemini-3.1-flash-lite out of preview, and the model picker on Personalization → AI Models now offers the GA identifier. Institutions on the preview model are upgraded automatically, with no behavior change. The preview identifier stops accepting requests upstream on May 25, 2026; pick the GA entry manually if you ever switch away and back.Personal API Key usage: Admins can now see which devices have used their personal API key. Open My Profile → Developer — API Key and expand Recent device usage for per-device rows with browser/OS family, IP subnet, an optional client name and hostname, first/last seen, and a call count. Rotating or revoking your key wipes the list. Forget device removes a row but doesn’t invalidate access — regenerate your key to do that. Records auto-expire 180 days after a device’s last sign-in.Conversation actions stay in the right Digital Twin: Renaming, deleting and summarizing a conversation now apply only to the Digital Twin you are in, so an action in one twin can no longer affect a conversation in another twin you belong to — most noticeable on mobile, where people switch twins often. The conversation list also restores the most recently used assistant for each conversation.Email-based two-step verification (admin opt-in): Admins now see a one-time prompt after login to enable email-based two-factor authentication. When on, password and OAuth logins from a new device or location trigger a 6-digit code emailed to the account, valid for 5 minutes. Trusted devices stay trusted for 7 days on the same network — paste-from-clipboard and auto-submit on the 6th digit, no button to click. Manage devices or toggle MFA from My Profile → Two-step verification; admins can override per user via Users → Edit → Credentials. Standard users can opt in but aren’t prompted yet. After 5 wrong attempts a code invalidates; after 5 burned challenges in an hour the account locks for 10 minutes. iOS Safari + Mail surface the code in the keyboard autofill bar.Reliable long-audio transcription: Long audio uploads (lectures, interviews, recorded meetings) no longer fail with “audio duration exceeds maximum” when compressed files were small in size but long in playback. Chunks are now sized against both limits, so a heavily compressed 75-minute recording splits into pieces the transcription model accepts. Files that previously failed can simply be re-uploaded.Reliable large text uploads: Large plain-text uploads (HR / medical / administrative exports, CSV/TSV dumps over ~16 MB) that previously failed during processing now succeed. Files that previously failed can be re-uploaded. Large .tif, .odt, .ods and .odp uploads are no longer rejected either.Reliable PDF export from your vault: Pria can now convert an existing markdown file in your vault to PDF without re-reading it — just point Pria at the source file by URL and the conversion happens in a single step. Together with recent fixes for accent and emoji rendering, French and multilingual letters now export correctly with proper bold headings and rendered emoji. Saving a file to a .pdf path renders the Markdown content directly.Simpler save: When you ask Pria to save a file, the filename and extension are now a single path (e.g. report.md or letter.pdf). This removes a class of bug where the requested format and the extension could disagree.Larger content reads: The default cap when summarizing scraped pages, transcribed media, and tool results is now 60,000 characters (up from 40,000) — useful for longer letters, articles, and transcripts.Memory Parameters page: Pria now exposes the running memory it uses to remember context about you — namespaces, key/value pairs, and per-instance shared knowledge — via a new My Profile → Memory entry (also under Pria → Settings → Personal → Memory Parameters). Personal entries are private to you; shared entries are scoped to a digital twin and visible to that instance’s members. You can edit values and descriptions, toggle the shared flag, delete a row, or bulk-delete a filtered selection with a preview before confirming. Members with the institutions.edit entitlement can also edit and clear shared rows for the instances they administer; everyone else sees those rows read-only.Admin Memory Inspection: Admins with the users.edit entitlement can inspect and manage any user’s memory from Admin → Users → Edit user → Memory. Memory is grouped by instance, and admins only see entries for instances they hold users.edit on. The same edit / delete / bulk-clear controls apply, with an authorization re-check on every change.Instance Memory Inspection: A new Instance Memory tab in Admin → Instances → Edit instance shows the shared memory scoped to that instance, with the author email linking to that user’s Memory tab when the admin holds users.edit on their institution.Act As (impersonation): Admins with users.edit can now impersonate a user from the Edit User modal via a new Act As… button. A consent dialog requires a written reason (up to 500 characters) and confirms the admin will see the user’s personal data and that every action is recorded as theirs. While impersonating, an amber Acting as <email> pill stays pinned in the top navigation, the rest of the admin console is unavailable, and Stop restores the admin’s session and returns to the Edit User modal. Sessions auto-expire after 1 hour, and every start and stop is recorded in an audit log with the reason, IP, and user agent. Self-impersonation, Praxis AI staff targets, and nested impersonation are blocked.Display Thinking Details (admin toggle): Pria now collects model reasoning from the providers that expose it (Anthropic, AWS Bedrock, Google Gemini, OpenAI summaries, xAI) and shows it in a collapsible 💡 lightbulb block above the response. Mistral doesn’t expose thinking, so no lightbulb appears. A new Display Thinking Details checkbox on the institution Personalization page (next to Display Tools Details) controls whether thinking is streamed, shown, and saved to History — defaults to on. Personal users always see thinking; institution accounts inherit the toggle.Safer bulk delete in IP Vault: The Select All button in the Files panel now respects your active filter — searching
scr_* and clicking Select All picks only the matching files, not the whole vault. The bulk-delete confirmation lists every collection and file to be removed in a scrollable preview so you can review before confirming. Collections are excluded from Select All while a search is active. No action required.Audio Notes: Capture spoken notes from the Pria toolbar. Tap the mic icon to open the Audio Notes modal, tap to start and stop (mobile-friendly toggle, no press-and-hold), and add as many segments as you need with playback, rename, and reorder. Hit Save and Pria transcribes in the background — notes appear in a new Audio Notes collection in your personal vault, each auto-titled from what you said. An optional Combine audio into a single note checkbox merges a session of short bursts into one note. Notes are linked to the active assistant and conversation, and token usage counts against your normal credit balance. Enabled by default for personal accounts and new twins; admins can disable it under Personalization → UI & Appearance → Disable Audio Notes for Users (also hidden in Guest UI or when file upload is disabled). On existing Digital Twins it starts off — admins turn it on.Large media & archive uploads flow through the queue: Long audio/video files that split into 10-minute chunks, and ZIP archives that expand into multiple documents, now appear as individual rows in the Files panel and process independently — each with its own live progress, retry budget, and final state. The parent row is hidden once its children are queued, and children expand automatically so you see exactly what was produced.Live file ingestion progress: Uploaded files now show live processing progress in the status tooltip with a percentage that climbs as the file is processed. The Files panel auto-polls in-flight uploads every few seconds, so you no longer need to refresh to see when a large PDF or video transcript is ready. Transient failures retry automatically; only terminal errors surface as “Processing failed”.More accurate model limits: The model picker now shows the correct input and output limits for several models on Bedrock, OpenAI, Gemini, Mistral and xAI. Nothing changes in how the models behave.Rename conversation with AI: The Manage Conversation dialog now has a Rename with AI button that suggests a short, descriptive title from the first and last few dialogues — mirroring Summarize with AI. Review the suggested name in the editable field and save with Update.Unified RAG segment size: The admin RAG Segments editor now uses a consistent 8,000-character soft cap across all embedding models. The new Ollama option mxbai-embed-large (1024-dim, 512-token context) auto-scales ingestion to safer smaller segments, and what gets indexed now matches what you can edit.Vector dimensions in the model picker: The embedding model picker now shows Vector Dim (e.g. 1536d, 3072d) in place of Output Size, making models easier to compare. Two new models were added: mxbai-embed-large (Ollama, 1024-dim) and gemini-embedding-2-preview (Google, 3072-dim, with a raised 8,192-token input limit).Friendlier custom-LLM auth errors: When an institution’s custom AI model (Bring-Your-Own-Token endpoint) rejects a request with a 401/403, users now see a clear “your administrator needs to verify the API key in Settings → AI Models” message instead of the raw upstream error. Diagnostic emails to admins include the offending model’s name, URL, and provider so misconfigurations are easy to identify.Tool-use uploads pinned to personal vault: Files saved via AI tools (generated images/audio/video, Google Drive downloads, URL scrapes) now always land in a standard user’s personal vault. Admins keep the existing behavior and can still route tool outputs to instance or account vaults.Cross-institution collection access: Fixed an issue where authorized admins got a 403 when opening collections (or adding/removing files) that belonged to another institution. The check now matches the entitlement-based behavior used elsewhere in the Files panel.Files panel stuck loading: Fixed a case where the Files panel stayed on “Loading, please wait…” after a failed collection fetch. It now falls back to the empty state so the error banner is visible and the panel stays usable.Embedded Files panel scroll loop: Fixed an infinite height growth when opening a collection from the admin Instances → IP Vault panel. The embedded Files container now uses a bounded viewport height.Claude Opus 4.7: Added support for Anthropic Claude Opus 4.7 on Bedrock (global.anthropic.claude-opus-4-7, us.anthropic.claude-opus-4-7) and the Anthropic Direct API (claude-opus-4-7). Opus 4.7 uses adaptive thinking with a native 1M input / 128K output context window (no extended-context toggle required). Opus 4.6 remains available and fully supported.Files entitlement system: IP Vault access is now governed by granular files.list, files.add, files.edit, and files.delete entitlements, so account admins can scope exactly who manages instance and account vaults. Standard users can no longer upload to instance vaults. Existing admin memberships are seeded with the new entitlements automatically — no action required. The Files panel shows only the actions each admin is entitled to.Personal upload gate enforced server-side: The institution setting Disable File Upload for Users is now enforced on the server — standard users get a 403 when uploading personal files (via file picker or URL) while it’s enabled. Allowed Email Domains for File Upload still carves out per-domain exceptions. Collections and existing files stay editable; the gate applies to new uploads only. The Files panel shows a Your access pill in Vault Health reflecting your entitlement when switching between personal, instance, and account vaults.Excluded Only file filter: The Files panel now has an Excluded Only toggle alongside Included Only, to quickly audit files not part of the RAG selection. The two are mutually exclusive; toggling a file’s inclusion while a filter is active removes it from the view.Video generation with Nova Reel and Sora 2: Video generation now routes through Amazon Nova Reel 1.1 (Bedrock, default) or OpenAI Sora 2 / Sora 2 Pro — configurable per institution from admin settings. Nova Reel makes 6-second clips from text or an image; Sora 2 makes 4, 8, or 12-second clips from text (Sora 2 Pro for higher quality). Video generation works in chat and convo modes — source image optional, aspect ratio (16:9 / 9:16 / 1:1) defaults to 16:9, and the MP4 saves to your IP Vault. Stability AI’s video endpoint was retired by the provider, so the Stability video model is now deprecated.Stability AI provider: Stability AI is now a provider (alongside OpenAI, Anthropic, Google, Mistral, xAI, and Bedrock) for image and audio generation. It adds audio generation (chat and convo modes) alongside image generation. Stable Audio 2 generates up to 190 seconds of audio from text, saved to your vault. Admins can pick per-category models (Image / Audio Generation) and override the API key per institution.Bedrock legacy model deprecations: Marked us.amazon.nova-premier-v1:0, cohere.command-r-plus-v1:0, and amazon.nova-canvas-v1:0 as deprecated after AWS flagged them Legacy, and added cohere.command-r-v1:0 as the active Cohere-on-Bedrock replacement. Institutions on the deprecated conversation models should switch to us.amazon.nova-pro-v1:0 / us.amazon.nova-2-lite-v1:0 or cohere.command-r-v1:0; for image generation, switch to a Stability or OpenAI model.Cross-twin conversation search: From the gallery, search your conversation history across all your active digital twins. Each result shows the matching twin with shortcuts to View the record or Go To the conversation directly — switching twins automatically when needed.Login security hardening: Strengthened security across every sign-in path — email/password, Google, GitHub, Facebook, custom OAuth2 SSO, and Pria SDK launches — protecting SSO logins from cross-site forgery, closing a password-validation edge case, and keeping one-time login codes out of browser history, server logs, and referrer headers. Existing sessions keep working; no action required.Fix — the Max Tokens setting is honoured by every provider: All providers (OpenAI, Anthropic, Google, Bedrock, xAI, Mistral) now correctly honor the institution’s “Max Tokens (Completion)” setting; previously xAI and Mistral ignored it and OpenAI defaulted to 32,000. “Unspecified (LLM Default)” now uses each provider’s native default, and “Auto” computes from the model catalog’s output cap. Bedrock thinking-mode users on “Auto” will see longer thinking budgets — pick an explicit value ≤16,000 if you hit throttling. “Unspecified” combined with thinking mode isn’t supported on Bedrock — use “Auto” or an explicit value ≥10,000.Admin edit modals: Every admin edit page (Instances, Accounts, Users, Assistants, AI Models, SSO, Tools, Questions, Feedbacks, Sessions, Histories, Saved States) now opens as a Lightbox over its list page, so you keep your scroll position, filters, and pagination. Prev/Next chevrons (and Ctrl+Arrow shortcuts) move between rows without closing the modal. Delete confirmations are now consistent Lightbox dialogs with an entity summary card. External deep-links (e.g. Canvas LMS SDK, Pria.js) continue to work.Institution lifecycle management: The admin Instances list now helps manage institution lifecycles. A status filter (Active | Inactive | All) switches views, and a Last Activity column shows a traffic-light dot (green within 30 days, yellow 30–90, red over 90). The Manage dialog offers Mark as Inactive on a stale active instance or Reactivate on an inactive one, and long-idle inactive instances (over 90 days) show a Ready for removal badge next to the Delete button.Inline account switcher: Admins with access to multiple accounts and the institutions.edit entitlement can reassign an instance to a different account directly from the Instances list — click the pencil next to the account name, pick a target, and confirm. The row updates in place without reloading.Last Activity on Accounts and Users lists: The admin Accounts and Users lists now show the same Last Activity column and stale indicator as the Instances list — traffic-light dots, relative time since last activity, and a yellow “inactive” hint for rows idle 30+ days — helping spot dormant accounts and users.Per-row entitlement scoping: Fixed an issue where an admin with membership in one institution saw Edit, Manage, and Delete on all rows in the Instances list — even institutions where they only had plain membership. Entitlement checks are now scoped per row, so admin actions only appear where you actually have permission.Sidebar UX redesign: Redesigned the Pria sidebar with a dedicated Conversation Model label and an entitlement-gated Configure button for jumping to model settings. Digital Twin and TTS Audio sections use a clean card layout, and new About RAG Modes and About Document Search help sections were added. The Tools section is now an always-visible scrollable list showing the enabled count. The “Load Max Dialogues” button was removed — infinite scroll handles it.Welcome screen enhancements: The Pria welcome screen now has flip cards that reveal descriptions on hover, a 3-column layout, and a subtle shimmer on the “What can I help with?” title. The streaming dialog uses a consistent input-box width and a colorful bouncing loader.Streaming scroll UX: A smoother streaming experience — your input and loader scroll into view immediately on submit, the completed dialog is fetched before clearing the stream to prevent jumps, and the view settles smoothly on the completed message.Admin Lightbox Manage modal: The Instances list Manage action is now a two-tier Lightbox (main + nested Confirm) instead of a popup. Release Credits is hidden when an instance has no parent account, and action buttons match their icon colors (amber for Recover, orange for Delete History). All admin list pages use a consistent action-menu wrapper.Base64 image support on custom LLMs: Custom OpenAI-compatible LLMs (Bring-Your-Own-Token) now accept base64-encoded images in the conversation, matching the native OpenAI provider — useful for vision-capable custom endpoints that don’t support URL image input.IP Vault UX improvements: Owners can now include/exclude, download, and move account-shared files regardless of their current institution. The Status badge (Included/Excluded) shows on all account-shared files, included files get a blue border, collection lists are deduplicated, and the Source field shows the assistant name with the instance in parentheses for clearer attribution.PDF OCR memory optimization: Reduced memory use during PDF OCR ingestion — page concurrency is capped, rendering scale was lowered, and file I/O is now async — preventing out-of-memory crashes on large image-based PDFs.Fix — long conversations on Anthropic models: Long conversations with a system prompt on Anthropic models no longer fail with an error.Android Chrome login fix: Fixed a blank blue page that some Android Chrome users saw after Google sign-in.Fix — “No Content” errors: An empty answer from an AI provider no longer shows a “No Content” error.Files panel stability: Fixed an issue where the Files panel could close unexpectedly when clicking the backdrop during upload, file move, or ingestion.Admin Instance About field: The About field in the admin Instance edit form is now a code editor with markdown syntax highlighting and a character counter, making long instance descriptions easier to write and proofread.Assistant RAG collections: Assistants can now be scoped to specific document collections in the IP Vault — the assistant’s retrieval only searches the selected collections, enabling focused assistants that reference specific knowledge bases while sharing the same IP Vault.Per-assistant tool configuration: Administrators can now control which AI tools each assistant can use. Set an assistant to “Selected Tools Only” and pick specific tools from the institution’s enabled set, with a filter toggle to view only selected tools or expand to the full list.Assistant-scoped RAG search: The standalone RAG Search tool and the MCP search now accept an optional assistant to scope results to that assistant’s configured collections. Results show collection names and the number of files searched, even when there are no matches.Faster RAG retrieval: Vector search across your vault is now significantly faster at scale.PDF OCR fix: Fixed an issue where image-based PDF pages failed OCR because the original PDF was sent to the vision step instead of the converted page image.xAI Grok provider: xAI is now an AI provider in Pria — conversations, tools, image understanding, speech and embeddings. Supports the Grok 3, Grok 3 Mini and Grok 2 Vision models.Updated AI models: Added GPT-5.4, xAI Grok-4.20, Stability AI image generation models, and new embedding models to the platform catalog. Gemini 3.1 Flash Live Preview is now the default for Google real-time conversations.Admin Personalization reorganization: Reorganized the Personalization tab with a dedicated Convo (Real-Time Speech-to-Speech) section, improved Document Summarization placement, and clearer sub-section visual hierarchy.Voice preview links: Added direct preview links to the OpenAI TTS Playground and Google AI Studio so you can audition a voice before selecting it.ElevenLabs credential warning: A warning pill now appears in the Personalization tab when the ElevenLabs Agent ID or API Key is missing, guiding admins to the Configuration tab.Canvas course filtering: Fixed an issue where conversation history wasn’t filtered by course context when launching Pria via the Canvas LMS SDK.Canvas section reorder: The Canvas integration section moved above Voice Cloning in the Configuration tab for better discoverability.Embedded Pria in restrictive LMS frames: Pria now works reliably when embedded in third-party LMS platforms with restrictive sandbox policies.Voice media embeds: Fixed an issue where media embed URLs in AI responses were corrupted by the voice sanitizer, preventing audio and video previews from rendering correctly.Documentation audit: Comprehensive update of all documentation to reflect current model catalogs, tool counts, voice providers, and admin UI layouts.RAG mode selector: Choose between three RAG modes — Normal (RAG-augmented responses), Search Only (returns only RAG results without AI generation), and Disabled (pure LLM responses). Available in the Pria sidebar, as a toolbar cycle button, and in your profile page.Admin Histories pagination & filtering: The admin Histories page now uses server-side pagination with infinite scroll instead of loading all records at once. Added a Course Name filter, and the charts (Model Distribution, Peak Usage Heatmap) now respect all toolbar filters including User, Account Type, Course, and Date Range.Admin server-side pagination: All 14 admin list pages now use server-side pagination with infinite scroll instead of loading all records at once — Users, Entitlements, Feedbacks, Institutions, Sessions, Accounts, AI Models, Assistants, Tools, SSO Providers, Payments, Saved States, Questions, and System Sessions. A “Showing X of Y” record count appears above each table, and additional pages load automatically as you scroll.- Mistral AI Native Provider: Added Mistral AI as a first-class provider — conversation, vision, reasoning, code, multilingual, TTS, STT, embeddings, and moderation models now run natively for better performance and full feature support
- YouTube URL Import: Paste a YouTube URL into the uploader and Pria automatically pulls the transcript with timestamps, video metadata, and thumbnail. Videos without captions can still be imported with Skip Indexing enabled, and re-ingesting refreshes the transcript and thumbnail
- Reprocess Content: Redesigned Reprocess Content dialog with dedicated cards for re-embedding and re-ingesting, a Skip Indexing option, and clearer error handling
- Skip Indexing: Upload files, URLs, or clipboard content to your IP Vault without indexing them for AI search — useful for storage-only files or content you want to index later. A per-file “Skip Indexing” checkbox is available on all upload tabs, and skipped files can be reprocessed anytime
- SSO Provider Management: Admins can configure OAuth 2.0 Single Sign-On providers from the Admin dashboard — set identity provider endpoints, client credentials, and field mappings, then assign them to institutions. Users sign in at
/sso/{slug}and are automatically logged in and enrolled, with connectivity testing and dark mode support on the SSO login page - File Preview: Enhanced fullscreen file preview with HTML document rendering (Preview and Source views), print support for all file types, and an open-in-new-tab button
- Guest Mode: Institutions can enable a minimal guest interface that hides the sidebar, file uploads, assistant switching, and profile menu — ideal for demos or guided experiences
- Lightbox Wizards: Create and Enroll Digital Twin flows now open as overlay modals above the Gallery, so you never lose your place while browsing
- Copy Feedback: Clipboard copy actions now show a smooth 3D icon-flip animation instead of popup alerts, with clean print output in both light and dark mode
- Gallery Favorites: Toggle favorite Digital Twins directly from the Gallery cards for quick access
- ElevenLabs Transport: Admins can choose the connection method for ElevenLabs voice conversations
- RAG Search Timing: Search results now show how long the search took, for performance transparency
- Google Document Upload: Paste Google Docs, Sheets, or Slides URLs directly into the uploader — content is read securely via Google OAuth. Supports personal and institution-level Google authorization, with context-aware prompts to connect your account when needed
- Google Slides Reader: Google Presentations are now fully supported in URL uploads, extracting text from all slides
- RAG Segments Panel: Improved segment management with metadata editing and a one-click reprocess workflow
- Gemini Live Stability: Improved reconnection handling for Gemini voice conversations, with automatic retry on unexpected disconnects
- Smarter Conversation Memory: Pria now compacts older conversation history into concise summaries while keeping your most recent exchanges verbatim, so longer conversations stay coherent and responsive without burning extra credits. Activates automatically when Remember History is set to 6 or higher
- Streaming Performance: Dramatically smoother AI response streaming, eliminating visible lag during long responses
- Typing Responsiveness: Fixed input lag during AI streaming — typing in the text entry bar is now instant even while a response is being generated
- Stripe Billing: Stripe-powered credit purchasing with personal and institutional packages, purchase confirmation screens, and a new admin Payments page with full payment history
- Conversation Manager: Manage conversations and favorites in Lightbox popups for a cleaner, more focused experience
- Mini Sidebar: Redesigned sidebar with hover expansion and instant search-as-you-type for quick access to conversations and tools
- Options Tray Redesign: Animated collapsible options panel with a soft glow border for a more polished settings experience
- Creation Wizard: Rebuilt the Digital Twin creation flow as an intuitive 8-step wizard with step animations
- PDF Generation: AI can now generate formatted PDF documents, with math symbols and special character support
- Drag & Drop Upload: Upload files by dragging them onto the interface or pasting from clipboard, with a new fullscreen file preview
- Code Editor: Rich code editor with live markdown preview for editing instructions, replacing plain text areas
- Summary View: Redesigned summary display with a loader animation and streamlined follow-up UI
- Multi-Provider Embeddings: Document search embeddings now support Bedrock Titan, Google Gemini, and OpenAI models, selectable per institution
- RAG Chunk Enrichment: Smarter document processing for more accurate search results
- Embedding Segments: New UI for creating and managing individual embedding segments
- OpenAI Realtime Enhancements: Noise reduction, configurable transcription language, and improved session defaults for Convo Mode
- Gemini Realtime Improvements: Fixed transcript accumulation and voice separation in Gemini-powered conversations
- Download Tracking: Upload view now surfaces download statistics and file usage analytics
- Vault Health: File integrity indicators visible for all users across all file statuses
- iPhone & QuickTime Audio Support: Upload
.movrecordings directly — Pria automatically extracts and converts the audio before transcription, so iPhone voice memos and QuickTime exports work seamlessly across all AI providers - API Key Authentication: Admins can now authenticate via API key for programmatic access — generate, view, copy, and revoke personal API keys directly from the Profile page
- Admin Histories Filter: New account type dropdown in the Histories admin page lets you filter conversation records by user or admin accounts, with filter state preserved across pagination
- Clipboard Restrictions: Institutions can disable copy/paste for non-admin users to protect sensitive AI-generated content, while admins retain full access
- Animated Loading Screen: Redesigned loading experience with an animated Pria logo, radial fade, and smooth fade-in transitions
- Bundle Optimization: Faster page loads through code splitting
- Security: Inactive or pending institution members are blocked from AI interactions; all active sessions are revoked on password change; Facebook login moved to server-side OAuth2; password policy enforcement; SVG sanitization; and vulnerability remediation
- Dark Mode: Fixed select dropdown and input background inconsistencies in dark mode
- File Downloads: Corrected file extension mismatches in downloaded files
- Deep Research: Reasoning effort automatically tuned for deep-research model configurations
- Uploads Access Control: Three access levels for files — owner, institution members, and shared
- iOS Safari: Fixed keyboard toolbar overlapping the chat input area on iOS Safari
- Gemini Flash Live: Added Google Gemini 2.5 Flash as a third real-time voice provider in Convo Mode, alongside OpenAI Realtime and ElevenLabs, with tool calling, transcription, and per-institution voice selection
- Claude Sonnet 4.6: Added support for Claude Sonnet 4.6 and set it as the new platform default model
- Gemini 3.1 Pro: Added Gemini 3.1 Pro to the model catalog
- GPT Realtime 1.5: Added OpenAI gpt-realtime-1.5 and set it as the default for Convo Mode
- Direct AI Providers: Introduced native Anthropic and Google GenAI providers for direct model access, improving performance and enabling full feature support (tool use, streaming, prompt caching)
- Reasoning Effort: Added configurable thinking/reasoning effort levels alongside max token settings for supported models
- Custom AI Models: Added validation for custom model configurations (API URL, API key) to prevent misconfiguration, plus deprecated-model indicators in the catalog
- File Collections: Organize files into nested collections with drag-and-drop, breadcrumb navigation, and animated transitions, plus a bulk edit mode for multi-select move, delete, and reprocess
- Files Redesign: Rebuilt the Files interface with a fast grid, infinite scroll, live upload progress indicators, and enhanced file cards with type-specific icons
- Upload Experience: Redesigned upload workflow with deferred processing, RAG segment editing, and Google Drive deduplication
- Chunked Audio/Video Transcription: Large audio and video files (>20MB) are automatically transcribed with speaker diarization support, raising the upload limit to 150MB
- Excel Legacy Support: Added support for older
.xlsExcel spreadsheets - History Compaction: Conversation history compaction keeps the 3 most recent exchanges verbatim while summarizing older context, reducing token usage in long conversations. Configurable per institution
- Extended Context: Added a toggle to enable 1M token extended context for supported models, shown only when the selected model supports it
- Vault Health: New health panel in the Files vault showing error counts, unused files, and content quality scores
- RAG Error Recovery: Files stuck in processing are now automatically marked as failed with a red indicator, and stale uploads (>15 minutes) offer one-click Delete or Reprocess
- Edit Assistant Redesign: Redesigned the Edit Assistant lightbox with improved variable management and dynamic variable mapping
- ElevenLabs Voice: Added ElevenLabs as a Realtime speech-to-speech voice provider with voice cloning support in Digital Twin personalization
- Google Tools in Convo Mode: Google services (Drive, Calendar, Gmail) are now accessible during voice conversations
- Session Analytics: New charts in the admin Sessions and Histories tabs — device type distribution, activity timelines, peak usage heatmaps, and model distribution with selectable chart types
- Google OAuth Multi-Institution: Added context-aware Google OAuth supporting authentication across multiple institutions with automatic token validation
- Account Manager Role: Introduced a new Account Manager role for managing multiple institutions within an account (contact humans@praxis-ai.com to request access)
- Enroll Users: Added an Enroll Users tab to the admin Entitlements page for streamlined onboarding with auto-loading of eligible users
- Platform Monitoring: Enhanced platform-level session monitoring with per-transport hourly stats and persistent client session history
- Admin Filtering: Added an AccountSelect filter across all admin list pages for easier multi-account management
- Security Hardening: Signed SDK launch tokens, field whitelisting on all update endpoints, hashed reset codes, rate limiting on auth endpoints, and privilege escalation fixes
- Dark Mode: Extended dark mode to loading dialogs, info banners, branding backgrounds, login buttons, and Canvas token cards across 18+ components
- Profile Auto-Save: Profile setting toggles now auto-save on change without a manual save action
- Feedback Redesign: Redesigned the feedback interface as a Lightbox modal for a more focused experience
- Touch Support: Added touch event support for improved mobile and tablet interactions
- Enrollment Search: Enhanced the enrollment page with keyword search
- Performance: Optimized file queries, assistant loading, connection handling, and session charts for faster page loads and fewer admin timeouts
- Dark Mode (Beta): Released
darkmode support in the Pria UI, with custom dark background images per institution - Digital Twin Gallery: Launched a browsable gallery for discovering and selecting Digital Twins, with ElevenLabs voice embedding support
- Text Entry Repositioning: Resized and repositioned the text entry bar to float over the conversation history for better visual hierarchy and more screen space
- Files and Assistants Layout: Repositioned Files and Assistants under the text entry bar for a more compact, streamlined display, with redesigned file and assistant cards
- Profile Picture Upload: Added the ability to upload profile pictures from webcam or file
- Sidebar Enhancements: Collapsible sidebar tray, direct tool enable/disable toggle, and a RAG-specific configuration panel
- Terminology Update: Renamed “Agents” to “Tools” across the platform; instances are now consistently called “Digital Twins”
- Institution Cloning: Administrators can now clone an entire institution configuration
- Streaming API: Added a Q&A streaming endpoint for real-time response delivery
- Prompt Optimization for 2026 Models: Tuned system instructions for the latest models (GPT-5.2, Claude 4.5, Gemini 3.0 Flash), prioritizing personality-first responses for more immersive Digital Twin experiences
- Tool Guidance Toggle: Added a switch to reduce instruction verbosity for general conversations while keeping full guidance for advanced research queries, improving response speed without sacrificing quality
- Model-Aware Response Tuning: Tuned responses to leverage the latest models’ capabilities — improved reasoning, fewer hallucinations, and better context retention across long conversations
- Voice Selection: Enhanced voice picker for Convo mode with an improved selection experience
- SDK Hardening: Improved SDK reliability with inactive-instance handling and membership validation
- File Cleanup: Added an automatic cleanup routine to remove orphaned files from deleted users and institutions
- Open AI GPT 5.2: Added support for the latest GPT 5.2 model from OpenAI.
- Manage Favorites: Rename and organize your favorites with custom descriptions or AI-generated summaries.
- GitHub Login: Added support for authentication via GitHub.
- Google Login: Enhanced authentication process for Google accounts.
- Account-Level Assistants: Assistants can now be shared at the account scope, making them instantly available to all digital twins within the same account.
- Account-Level RAG Files: Documents can now be promoted from Instance to Account level, giving every digital twin in the account access to a shared knowledge base.
- History Graph: Now defaults to the last 12 weeks with daily data shown as a bar chart.
- Assistant Filtering: Added a toggle to quickly filter assistants by type: Personal, Instance, or Account.
- Model Tracking: Automatically records which AI model was used for content summarization and image analysis when uploading files and URLs.
- Sonnet 4.5: Added support for the Claude Sonnet 4.5 model and set it as the platform default.
- All Anthropic Models: Upgraded plans to support large input context up to 1 million tokens.
- Canvas tools: Canvas lookups and Canvas search now run at the same time, so answers arrive sooner.
- Content Length Returned by Tools: Tools now return up to 60,000 characters (increased from 20,000).
- Assistants Features: New options to disable RAG searches when running assistants, and to run assistant instructions without system context.
- Pria JS SDK: Added a
pria.isReady()function that returns whether Pria is ready to receive messages. - File Import Enhancements: Improved support for ZIP and IMSCC file imports.
- Shared Memory: Added shared memory that stores information accessible across all users of the same digital twin, enabling cross-user persistence and collaboration.
- Memory enhancement: Memory now supports both user-specific and shared memory.
- Privacy Policy Enforcement: Introduced account-level privacy policy settings that require users to accept terms before accessing Digital Twins.
- Selective File Upload Authorization: When file upload is disabled for users, administrators can authorize selected user groups by email domain suffix.
- Selective Assistant Authorization: When Assistants are disabled for users, administrators can authorize selected user groups by email domain suffix.
- Favorite Digital Twins Priority: Digital twins marked as favorites now appear first in the gallery carousel for easier discovery and quick access.
- OCR for Image-Based PDFs: Image-based PDFs (with no extractable text) now automatically undergo OCR for text extraction and indexing.
- Enhanced Date Range Selection: Administrators can now filter history and session records using a date range picker.
- Documentation Updates: Comprehensive updates covering RAG (Retrieval-Augmented Generation), Bring Your Own Token (BYOT), the Canvas tools, and more at https://docs.praxis-ai.com
- Anthropic Sonnet 4.5: Support for Claude Sonnet 4.5 (20250929) with a 200K context window, 64K output tokens, and enhanced multimodal capabilities including vision, document analysis, and tool use.
- MCP Server: Introduced an MCP Server that lets any AI solution call your Digital Twin.
- Security & Performance: Improved RAG security and performance.
- REST APIs: Expanded functions in the Runtime and Admin REST APIs.
- Documentation: Major updates—especially for Assistants, Canvas integration, and MCP at https://docs.praxis-ai.com
- Convo Mode Input: Added text input for conversations in full screen; reply by text while receiving vocal responses.
- Transcripts in Full Screen: Live transcripts available during Convo mode in full screen.
- Password Reset: Users can be required to reset their password on next login.
- Logged Remote Calls: Remote connector (MCP) calls are now logged in Tools Details.
- Gepetto Digital Twin: Improved AI Portrait Artist for generating Digital Twin avatars.
- Moderation by Default: Moderation is now enabled by default when creating new Digital Twins.
- Connector MCP: Added support for Remote Model Context Protocol (MCP) servers, individually configurable for each Digital Twin instance.
- Custom LLM Integration: Support for custom Large Language Models (LLMs) with per-Digital Twin configuration, letting organizations deploy specialized models for specific use cases (e.g. Vertex).
- Digital Twin Gallery Enhancements: Improved navigation with intuitive arrows and resolved display flickering on macOS for smoother interactions.
- OAuth Verification for Canvas Integration: Added mandatory OAuth 2.0 authentication for Canvas Theme SDK access, ensuring secure user verification before Digital Twin initialization.
- Streamlined Digital Twin Creation: A simplified 2-step Digital Twin creation process directly through the Gallery, reducing deployment complexity and time-to-value.
- Support for Mermaid diagrams and charts: Added support for Mermaid Diagramming and Charting.
- User Experience: Enhanced digital twin loading for standard users.
- Branding: Added branding for personalized login/signup.
- Text Customization: Customizable activation and joining messages.
- Logo Branding: Added a logo option for login sequence customization.
- Animation: Added animated picture support for Digital Twins.
- Token Management: Improved Canvas faculty token refresh.
- Digital Twins: Added a gallery for twin selection and management.
- REST Tools: Custom REST-enabled tool creation for instances.
- Email Notifications: Enhanced approval workflow notifications.
- Speech Features: Retired a deprecated speech component.
- Accessibility: Improved contrast ratios and ARIA labels.
- Substitution Variables: New prompt variable management system.
- Email Tool: New email functionality.
- Conversation Persistence: Added save/restore for your last conversation.
- Search Enhancement: Integrated Exa.ai for semantic web search.
- xAI Integration: Added support for xAI models.
- SDK Toolkit: Enhanced UI development capabilities.
- File Upload: Expanded support for all file types across platforms.
- Credit Transfers: Enhanced account-to-instance credit management.
- File Tools: Pria can now look through your document collections.
- Instance Management: New comprehensive admin management system.
- Performance: Improved file loading with asynchronous summaries.
- Pricing: Decreased costs across personal accounts.
- Email Processing: Improved email content parsing.
- Platform Upgrade: Backend updates for improved compatibility and stability.
- Streaming: Enhanced conversation streaming.
- Canvas Scoping: Added course ID filtering for history records.
- Assistant Management: Made user assistants admin-visible for sharing.
- AI Models: Added Claude 3.7 Sonnet support.
- Conversation Mode: Extended user access to conversation features.
- File Management: Enhanced file handling and RAG integration.
- Mistral Integration: Added direct API access for Mistral models.
- Bug Fixes: Resolved styling and file system errors.
- Accessibility: CSS improvements for users with epilepsy.
- Canvas SDK: Updated to version 1.3 with enhanced user ID handling.
- Security: Addressed third-party component vulnerabilities.
- Navigation: Improved UI layout for large screens.
- Canvas: Pria can now look up more of your Canvas course information.
- SDK Features: Added browser messaging capabilities and documentation.
- Data Compliance: Added DPA compliance features for data deletion and recovery.
- Canvas Integration: Added a discussion bot plugin.
- Token Management: Enhanced Canvas token refresh.
- Database Improvements: Improved database performance.
- Reliability: Improved retry handling for model requests.
- Analytics: Added tool usage tracking and metrics.
- Instance Management: Added the ability to disable specific assistants per instance.
- Email Notifications: Added low-credit alerts for administrators.
- Location Services: Enhanced web search with location-based results.
- Document Summarization: Improved summarization quality and reliability.
- Course Management: Added courses in the sidebar for institutional scoping.
- Canvas tool: Enhanced interpretation and display capabilities.
- Student Analytics: New feature to analyze student questions.
- Assistant Features: Launched new Assistant functionality and a Course Syllabus Generator.
- Bug Fixes: Resolved input size limitations and tool usage issues.
- Admin Enhancements: Multi-select instance support and Gemini Flash 1.5.
- LTI Brightspace: Bug fixes for course parameter passing.
- SSO Integration: Implemented QuickLaunch SSO OAuth.
- Credit Management: Added admin ability to transfer credits between accounts.
- AI Models: Added support for o1-preview and o1-mini models.
- Scalability: Fixed entitlements listing performance issues.
- Scientific Literature: Added a CrossRef tool for academic research support.
- Real-time Communication: Implemented OpenAI WebRTC APIs with UI.
- Voice Features: Enhanced voice selection capabilities.
- Canvas Integration: Captured global ID for Canvas OAuth tokens.
- User ID Updates: Relaxed user ID requirements to support string format.
- UI Improvements: Various interface enhancements and bug fixes.
- UI Enhancements: Implemented anchor text conversion for links.
- Copy Functionality: Added copy-input-to-clipboard feature.
- Timeout Resolution: Fixed response timeout issues.
- SDK Integration: Developed embed SDK for LMS integration.
- Personality Customization: Added ability to swap AI personalities per institution.
- Code Block Support: Enhanced parsing for multiple code blocks.
- Image Display: Added HTML image tag support.