Configuration and Integrations

The instance editor is where a Digital Twin is configured. It is organised as a tab bar across the top, and within each tab a set of section headings (with a quick-access rail to jump between them). This page mirrors that structure exactly, so a heading here is a heading you can see on screen.

Configuration and Integrations

Instance details, membership, AI behaviour, quotas, and every third-party integration.

Personalization and AI Models

Identity and branding, plus the model assigned to each job the twin does.

Knowledge and tools

RAG and Files, Connector MCP and Tools, Assistants, Onboarding Questions.

Twin Memory

Long-term Memory and Shared Memory.

How the instance editor is organised

This editor is available to Digital Twin Instance Admins. Depending on your entitlements, some fields are read-only, and a few are visible only to Praxis super-admins.

Two tabs are always present. The remaining tabs appear only after the instance has been saved — when you are creating a new instance you will see just the first two, and the rest unlock once it exists.

Tab	What lives there	Documented
Configuration and Integrations	Instance identity, membership and credits, AI behaviour, quotas, voice entry points, and every external service	On this page
Personalization and AI Models	Name, avatar, branding, UI, and the model chosen for each job	Personalization, AI Models
Connector MCP and Tools	External MCP connectors and the platform tool policy	MCP Servers, Tools
Onboarding Questions	The guided questions new users answer on first run	Onboarding Questions
RAG and Files	Retrieval settings, the ingestion pipeline, and the IP Vault itself	Knowledge & RAG
Assistants	Which assistants users may reach, and who may author them	Assistants
Agents	Autonomous agent workspaces. Appears only when the twin is agent-eligible	Agents
Twin Memory	Long-term Memory and Shared Memory	Twin Memory

Within a tab, use the quick-access rail beside the form to jump straight to a section heading rather than scrolling. On narrow screens the rail collapses and the headings stay in document order.

Instance Management

Instances are the core of your Praxis AI experience, allowing you to manage and interact with various digital twins.

Start by clicking the Admin dashboard, located at the top of the main user interface. The Instances tab displays all instances your user is entitled to manage, and also allows you to create a new instance if you are entitled to do so.

Viewing Instances

List of Instances

The Instances tab displays all instances you have access to. Each instance is listed with its name, status, and other relevant details.

Instance Details

Clicking on an instance opens the editor described below — configuration, members, and activity.

Depending on your administrative rights, your editing privileges may be limited.

Tab: Configuration and Integrations

This tab carries two top-level sections — Configuration and Integrations.

Configuration

Instance Details

Name

Set your instance name using consistent naming conventions:

Canvas integration: instance_name.school_name.instructure.com
Praxis LXP integration: instance_name.praxislxp.com

Instance Credits

The credit balance for this instance. New instances receive 50 starter credits. Purchase additional credits at https://pria.praxislxp.com/my-profile/pricing or contact your institution’s IT administrator for enterprise options.

To adjust this field, contact the Praxis AI team at humans@praxis-ai.com.

Status

Controls instance availability:

Active — Instance is operational for all users
Inactive — Instance is temporarily disabled

To adjust this field, contact the Praxis AI team at humans@praxis-ai.com.

Public ID

Unique identifier automatically generated during instance creation. Used for API integrations, Chat Completions, and system connections. This field is read-only — use the copy button to copy it to your clipboard.

Contact Emails

Specify administrator email addresses (comma-separated) for instance monitoring and notifications. Used for moderation alerts and system notifications.

Account

Links your instance to an institutional account for centralized credit management and distribution across multiple digital twins. Select from available accounts in the dropdown.

Access & Membership

Allow Joining

Controls how new users can join this instance:

Disabled — Users cannot self-join; they must be added by an administrator
Account only — Only users within the same institutional account can join
Everyone (public) — Anyone can join this instance

To adjust this field, contact the Praxis AI team at humans@praxis-ai.com.

Joining Admin Only

When enabled, only administrators can join the instance — regular users are blocked from self-joining. This option appears only when Allow Joining is set to “Account only” or “Everyone (public)”.

To adjust this field, contact the Praxis AI team at humans@praxis-ai.com.

Pool Credits

Enable credit sharing across all instance users. Each interaction consumes credits based on complexity. When credits are depleted, users cannot interact until credits are replenished according to your service agreement.

When Pool Credits is disabled, requests from users draw from each user’s personal credit pool instead.

Credits Awarded to New Users

The number of credits automatically granted to new users when they first join this instance. Set to 0 to disable automatic credit awards. This field is only visible when Pool Credits is disabled (i.e., users manage their own credit balance).

Grant Entitlements to New Admins

Automatically grants full entitlements to new administrators, providing complete dashboard access and customization capabilities. For specific entitlement questions, contact humans@praxis-ai.com.

Prevent Switching to Other Instances

When enabled, users are locked to this instance and cannot navigate to or switch to other Digital Twin instances. Useful for kiosk-style deployments or single-purpose integrations.

Disable Add Credits

Hides the option for users to purchase or add credits to their account. Use this when credit management is handled exclusively by administrators or through institutional agreements.

Prevent Personal Account Creation

When enabled, members of this instance are not offered a personal Pria account, and the option is unavailable to them.Two boundaries are worth knowing:

The setting applies while a member is working in this instance. Someone who also belongs to another instance without this setting can still create a personal account from there.
It covers members creating an account for themselves. Administrators adding or editing people through the admin screens are not restricted by it.

AI Behavior

Content Moderation

Screens every user message for unsafe content before it reaches the AI model. Flagged messages are blocked with a safe response, and an alert email goes to the instance’s Contact Emails.

Field	Description	Default
Enable Moderation	Turns content screening on or off	On
Moderation Model	The moderation model to use (e.g., `omni-moderation-latest`)	`omni-moderation-latest`

For the category taxonomy, model options, what users see when a message is blocked, and how to review flagged conversations, see Content Moderation.

Cite Sources

When enabled, the Digital Twin always includes source citations in its responses. This instructs the AI to reference the documents, files, or knowledge base entries it used to generate each answer, improving transparency and traceability.

Don't Prompt to Personalize

Disables the initial personalization popup for new users, allowing direct access to the conversation interface without being prompted to set preferences first.

Use Location

Enables location-based responses for queries about local services, weather, campus information, and regional content. Improves response accuracy and relevance for location-dependent requests.

History Compaction

Controls automatic conversation history management to keep conversations within AI model context limits.When enabled, Pria uses LLM summarization to compress older messages in long conversations. This allows conversations to continue indefinitely without losing context — earlier messages are summarized rather than truncated.How it works:

As a conversation grows, Pria monitors the total token count
When approaching the model’s context limit, older messages are grouped and summarized by an LLM
The summaries replace the original messages, preserving key context while reducing token usage
Base64-encoded data (images, files) is automatically stripped from compacted history
Tool results are enriched with human-readable summaries before compaction

History compaction is recommended for instances where users have long, ongoing conversations (e.g., research projects, multi-session tutoring). For short Q&A interactions, it’s unnecessary.

The K-Mean Score field is a retrieval setting, not a compaction one — it sets the relevance floor for knowledge search, and lives under RAG and Files. See Knowledge & RAG Configuration.

Transparency toggles

Five independent switches decide what users see alongside each response. All default to on; turn them off for kiosk-style deployments where the conversation should feel chat-like rather than tool-driven.

Display RAG/KAG Search Details — which passages were retrieved, and their relevance scores
Display Thinking Details — the model’s reasoning trace when thinking is enabled
Display Thinking Execution — live progress while the model is reasoning
Display Tool Execution — real-time progress as tools execute
Display Tools Details — the complete agent step-by-step breakdown

Disable Clipboard for Users

Prevents non-admin users from copying AI-generated content from conversations. When enabled:

Text selection is disabled on AI responses and user inputs
Copy keyboard shortcuts (Ctrl+C / Cmd+C) are blocked
Copy-to-clipboard buttons are hidden
Share link buttons are hidden

Administrators retain full clipboard access regardless of this setting.

Useful in exam or assessment environments, intellectual property protection scenarios, or when AI-generated content must not be easily extracted.

Autonomous Agent

A single switch that makes this Digital Twin eligible to run as an autonomous agent. Turning it on reveals the Agents tab, where you provision and manage the agent’s workspace.

This setting is super-admin only. If you need it enabled, contact humans@praxis-ai.com.

User Quotas

Per-user credit caps for this instance, shown alongside any caps inherited from the parent account and a live count of how many users are currently at their limit. Caps limit how much a single user may consume without affecting the instance’s total balance. See Credit Management for how caps interact with pooled credits and account-wide limits.

Realtime / Convo

The entry points to live voice. Provider choice, voice selection, and avatar tuning live in the Personalization and AI Models tab — see Realtime Voice & Avatars.

Enable Convo (Speech-to-Speech)

Activates real-time voice communication. Users can speak directly to the Digital Twin and receive verbal responses in real time. See Convo Mode.When enabled, the additional Convo settings below appear.

Convo Admin Only

Restricts Convo Mode to administrators — regular users will not see the Convo button.

Convo Enable Text Input

Allows users to type text messages during a Convo session in addition to speaking.

Lock full-screen conversation

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. Use this for kiosk screens and embedded experiences.

Start Immersive Mode by Default

Launches the voice conversation automatically after sign-in — visitors land in the immersive voice experience (with a tap-to-start step) every time, instead of the classic chat.

Convo Web Access Link

A short public web address that opens this Digital Twin for people with no Pria account — for example nova produces …/twins/nova. Once saved, the full link is shown with a copy button and a scannable QR code for posters, badges, and screens.Whether that page opens straight into a voice conversation is decided by Start Immersive Mode by Default; if voice isn’t available it falls back to text chat.

Anyone with the link can talk to the twin and consume credits from the pool it bills to. There is no separate publish switch — setting the address makes the twin reachable, and clearing it takes the page offline.

Full guide: Guest Twin Links.

Text-To-Speech

Controls the read-aloud voice used to speak responses in text conversations (distinct from Convo, which is a live voice call).

Field	Description
Use natural voices for read-aloud	Use a high-quality neural voice instead of the browser’s built-in speech synthesis
Speech model	The text-to-speech model that generates the natural voice (the platform default unless you pick one). The voices offered below follow this model — for example Ballad and Verse exist only on `gpt-4o-mini-tts`.
Read-aloud voice	Which voice to use when natural voices are on; only the voices the speech model can speak are listed

Integrations

Connect your Digital Twin to external platforms and services.

Embedding & LTI

Public Authorized URLs — the URLs authorized to embed or call your instance. All inbound requests are validated against this list.

https://<your_school>.instructure.com
https://<your_school>.beta.instructure.com
https://canvas.instructure.com

For hostname matching rules (subdomains, ports, what a broad entry authorizes), see Branding & Public URLs. LTI Contexts are populated automatically when you connect an LTI placement. The system remembers which instance to launch when a user arrives through LTI or a Canvas theme integration. To disconnect, remove the placement from this list or manage it from your profile page.

Pria MCP Server

MCP (Model Context Protocol) is the open standard for connecting AI to external systems, and your Digital Twin speaks it in both directions. Outbound — the twin calling external MCP servers as extra tools — is configured on the Connector MCP and Tools tab. The settings here govern the inbound direction and the identity signing used on outbound calls.

Enable MCP Server

Switch for the inbound MCP endpoint: when enabled, external MCP clients (Claude, agents, partner platforms) can call this Digital Twin as an MCP source — for example to search its knowledge vault — authenticating with the MCP Server Secret below.This switch does not affect outbound connectors: the MCP servers your twin calls as tools stay active regardless.

MCP Server Secret

Unique authentication token used when this Digital Twin exposes itself as an MCP endpoint. Generated automatically; can be rotated. Configure third-party MCP clients with this secret.This secret is the only accepted credential for inbound MCP. The Digital Twin’s Public ID is not a credential and will not authenticate an MCP call.

MCP Signing Secret

Shared key your integration partners use to verify the signed learner identity that rides on every outbound MCP tool call — so their servers can safely expose per-learner tools, trusting that the identity comes from the login session rather than from text the AI generated.Share it through a secure channel (not email). Regenerating is an immediate cutover — partners verifying signatures reject calls until they configure the new value — so coordinate before rotating. See Verified learner identity on tool calls.

Curation

Allows an external learning platform to request curated articles from this Digital Twin via POST /api/curation/search. Used by the Praxis LXP to populate its AI Curated Content library.Switching Curation on generates a secret the first time. Give that secret to the calling platform; it is sent as Authorization: Bearer <secret>. It is scoped to the Digital Twin rather than to a person, so curation keeps working when staff change roles.To stop curation, switch Curation off. Do not blank the secret — turning the flag off refuses calls cleanly, whereas an emptied secret makes the calling platform look misconfigured instead.

For the full MCP setup — authoring per-server configurations, supplying credentials, and exposing your twin as an MCP source — see MCP Servers.

Canvas

Connect your Digital Twin to Canvas LMS so it can query courses, assignments, grades, and more through the Canvas REST APIs. Without these credentials, the call_canvas and search_canvas tools are unavailable.

Canvas Client ID

The numeric identifier from your Canvas Developer Key (e.g., 10000000000217). Generated when a Canvas administrator creates an API-type Developer Key under Admin → Developer Keys.One Developer Key can be shared across multiple Digital Twin instances within the same institution.

Canvas Client Secret

The secret key paired with the Client ID above. Click Show Key on your Canvas Developer Key to reveal and copy it. Together these enable OAuth2 so users can authorize the Digital Twin to access Canvas on their behalf.

Canvas Faculty Access Token

A personal access token generated by a registered course instructor. Optional, but required for teacher-level operations such as posting grade comments, creating announcements, or bulk grading — actions that need instructor-scoped permissions even when the end user is a student.To generate one: in Canvas, go to Account → Settings → New Access Token.

This token grants instructor-level access to the courses the faculty member is enrolled in. Store it securely and rotate it periodically.

Canvas API Scopes

A whitelist of Canvas REST API endpoints your Digital Twin may call. Each scope follows the syntax:

url:<HTTP_METHOD>|<API_ENDPOINT>

For example: url:GET|/api/v1/courses/:course_id/smartsearchScopes must be configured in two places — on the Canvas Developer Key and here. If a scope is missing from either location, the API call is rejected.

During development, disable scope enforcement on your Canvas Developer Key to discover which endpoints your twin needs. Monitor Agent Details in your dialog history to see which API calls are made, then add those scopes here for production. Use the Upload/Download buttons to manage the list from a JSON file.

See Canvas Scopes Reference for the full list.

For a complete walkthrough — creating the Developer Key, configuring scopes, testing, and troubleshooting — see the Canvas Pria Tools guide.

Chat Completion

Exposes this Digital Twin behind an OpenAI-compatible Chat Completion endpoint, so external tools that already speak that protocol can talk to your twin.

Field	Description
Enable Chat Completion endpoint	Turns the endpoint on
Chat Completion Model	Which model serves requests arriving on the endpoint
Chat Completion Max Output Tokens	Ceiling on response length
Chat Completion Reasoning Effort	Reasoning depth, for models that support it

Requests authenticate with the instance API key — see API Keys below.

Anam Meeting Bot

Credentials and behaviour for the meeting agent that can join a Zoom, Meet, or Teams call as a participant, appearing with the twin’s avatar and voice. Engagement mode, naming, wake-words, pronunciations, and answer length are all documented in Meeting Agent; avatar and voice tuning itself lives in Realtime Voice & Avatars.

ElevenLabs Voice Cloning

Connect your Digital Twin to an ElevenLabs Conversational AI agent to enable voice capabilities — both for Convo Mode and for embeddable client widgets. Two credentials are entered here:

ElevenLabs Agent ID — the Agent ID from your ElevenLabs Conversational AI agent
ElevenLabs API Key — authenticates requests between ElevenLabs and your Digital Twin; must match the key in your ElevenLabs agent’s Custom LLM settings

If no institution-level API key is set, the system falls back to the platform-wide ElevenLabs key (if configured).

Once saved, select ElevenLabs as the Convo Mode provider under Personalization and AI Models — see Realtime Voice & Avatars. For end-to-end setup, see the ElevenLabs Voice Agent guide.

Anam Avatar

Credentials and tuning for the Anam photorealistic avatar used in Convo Mode. Configuration lives in Realtime Voice & Avatars.

Cartesia Voice

Credentials and voice selection for Cartesia, one of the Convo Mode voice providers. See Realtime Voice & Avatars.

Anam Avatar and Cartesia Voice both listen through Deepgram Flux, configured by the Speech Recognition Model field at the end of the Convo section in the Personalization and AI Models tab. OpenAI GPT-Realtime, Gemini Live, ElevenLabs, and xAI transcribe inside their own realtime connection and ignore that field.

Google

Enable Google Workspace services (Gmail, Drive, Calendar, Sheets, Docs, Slides, Meet, Classroom). You choose between two identity models: each user connects their own Google account, or you turn on Use Digital Twin Identity and connect one shared institutional account via the Connect Google Account OAuth flow. The full walkthrough — service capability table, dependencies, the two connection models, and the connect/disconnect flow — is on Cloud Services; see also the Google Workspace Integration guide.

When institution-shared credentials are active, they take precedence over any personal Google credentials a user may have configured. If an admin connects a shared Gmail, all users will use that shared Gmail — even if they have also authorized their own personal account.

Microsoft

Connect Microsoft 365 services using the same two identity models as Google.

Field	Description
Enable Access	Turns Microsoft services on for this instance
Use Digital Twin identity	Use one shared institutional account instead of each user connecting their own
Microsoft tenant (optional)	Restrict sign-in to a single Microsoft tenant

See Cloud Services for the connect and disconnect flow.

Kaltura

Connect to the Kaltura Video Platform for video search, playback, and media interactions. Enter your Partner ID and API Secret (plus a Client ID when using a user-level secret) — see Cloud Services for where to find each value in the Kaltura Management Console.

Amazon Web Services

Connect your own AWS services — primarily Amazon Bedrock for model access and Amazon S3 for storage — so the twin uses your AWS account under your organization’s billing and security policies.

AWS Region

The region where your services are deployed. Choose the one closest to your users or where your Bedrock models and S3 buckets are provisioned.

us-east-1 (N. Virginia) — Broadest Bedrock model availability
us-west-2 (Oregon) — Good Bedrock coverage
eu-central-1 (Frankfurt) — European data residency
ap-southeast-1 (Singapore) — Asia-Pacific

Not all Bedrock foundation models are available in every region. Check AWS Bedrock model availability.

AWS Access Key ID

The access key ID from your AWS IAM credentials. Generate this in the AWS IAM Console by creating an IAM user or role with the necessary Bedrock and/or S3 permissions.

AWS Secret Access Key

The secret access key paired with the Access Key ID. Shown only once when you create the IAM credentials — store it securely.

This is a sensitive credential. It is stored encrypted and excluded from API responses by default. Never share it in client-side code or logs.

IAM Permissions: Your IAM user or role needs:

Amazon Bedrock — bedrock:InvokeModel, bedrock:InvokeModelWithResponseStream, and bedrock:ListFoundationModels
Amazon S3 — s3:GetObject, s3:PutObject, and s3:ListBucket on the relevant buckets

Follow the principle of least privilege.

API Keys

By default the Digital Twin uses Praxis-managed credits for every AI provider. When you provide your own API key, the twin routes that provider’s requests directly to your account — bypassing Praxis credits for that provider and giving you control over billing, rate limits, and model availability. This is the bring-your-own-key (BYOK) section.

How BYOK routing works: when a model is selected for a Model Use and an API key exists for that model’s provider, the request bypasses Praxis credits and routes with your key. If no key is set, it falls back to Praxis credits. The fallback is per provider, so you can BYOK for OpenAI while still using Praxis credits for Anthropic.

OpenAI API Key

Connects to OpenAI models including GPT-5.2, GPT-5.1, GPT-5-mini, o4-mini, GPT-Image-1.5, and Whisper transcription. Also enables image generation and GPT-Realtime voice.Generate your key at platform.openai.com/api-keys.

Anthropic API Key

Connects to Anthropic Claude models including Opus, Sonnet, and Haiku. Enables extended thinking and reasoning where available.Generate your key at console.anthropic.com/settings/keys.

Gemini API Key

Connects to Google Gemini models including Gemini 3.1 Pro, Gemini 3 Flash, Gemini 2.5 Flash, and Gemini Live for real-time voice.Generate your key at aistudio.google.com/apikey.

xAI API Key

Connects to xAI Grok models including Grok-4, Grok-4 Fast Reasoning, and Grok Code Fast.Generate your key at the xAI Console.

Mistral API Key

Connects to Mistral AI models via the native SDK — Mistral Large, Medium, Small, Pixtral (vision), Magistral (reasoning), Codestral (code), Voxtral (TTS/STT), and embedding/moderation models.Generate your key at console.mistral.ai/api-keys.

DeepSeek API Key

Connects to DeepSeek models including DeepSeek-V3 and DeepSeek-R1 (reasoning).Generate your key at platform.deepseek.com/api_keys.

To enable this field for your institution, contact humans@praxis-ai.com.

Cohere API Key

Connects to Cohere models including Command A. Enables Cohere’s retrieval-augmented generation and enterprise search.Generate your key at dashboard.cohere.com/api-keys.

This section also accepts keys for Kimi (Moonshot AI), Stability AI, OpenRouter, RunPod, and InferX, plus the voice/avatar providers ElevenLabs, Anam, and Cartesia (which also take an Agent/Avatar ID).

Security: All API keys are stored encrypted, excluded from API responses by default, and never exposed to the browser. Only administrators with the appropriate entitlements can view or modify them.

Tab: Personalization and AI Models

Identity and appearance, plus the model assigned to each job the twin performs.

Personalization (Digital Twin)

Sub-section	What it covers
Name & Avatar	The twin’s display name, AI name, and profile picture
Content & Behavior	Digital Twin Instructions, tone, and behavioural guidance
UI & Appearance	Theme (dark/light, or follow the user’s system preference) and Custom CSS for branding

Custom CSS is injected as-is into the page. Test thoroughly to avoid breaking the layout.

Full reference: Personalization and Branding & Public URLs.

AI Models

Each Model Use — a job the twin does — is assigned a model here.

Sub-section	What it covers
Custom Models	Bring-your-own-model entries added to the catalog
Conversation & Reasoning	The main conversation model, reasoning effort, and thinking
Convo (Live Voice & Avatar Calls)	Realtime provider, voice, avatar, VAD, noise reduction, transcription language, and the Deepgram speech-recognition model
Media	Image generation, image analysis, audio and video models
System	Background jobs — summarization, embeddings, moderation, knowledge analysis, and subagent role models

Full reference: AI Models, Realtime Voice & Avatars, and Platform Models.

A provider’s key must be set in API Keys before its models become selectable here.

Tab: Connector MCP and Tools

Connector MCP

Outbound MCP connectors — external MCP servers this Digital Twin may call as extra tools. Each connector is authored with its own configuration and credentials. See MCP Servers and Connectors.

Tools

Governs which platform tools the twin may use.

Disabled Tools

A multi-select of platform tools the Digital Twin should not use on this instance — e.g. disabling generate_image for a text-only academic instance, or hiding call_canvas when Canvas is not configured. Tools are excluded from the model’s tool list at request time, so even if the model tries to call them the request is rejected upstream.

Tool Result Size Limit

Default: 60000 characters.Maximum characters returned by a single tool call; longer results are truncated. Increase for instances working with large documents or detailed API responses. Decrease to reduce token usage and protect against runaway tool output.

Full reference: Tools.

Tab: Onboarding Questions

The guided questions new users answer on first run, whose answers feed the twin’s understanding of each person. See Onboarding Questions.

Tab: RAG and Files

How the twin retrieves from the IP Vault, and the vault itself.

User Access

Who may upload, and the per-user file policy — including whether personal-vault content is searchable on this instance.

Ingestion Pipeline

How uploaded files are chunked, sanitized, and enriched before they become searchable.

RAG

Retrieval mode (Disabled / Normal / KAG Fusion / Search Only), chunk limits, the kmeanScore similarity threshold, and the embedding model.

KAG (Knowledge Graph)

Knowledge-graph extraction over ingested documents, and the analysis model that performs it.

Files in IP Vault

The vault itself, embedded directly in the tab — upload, preview, edit segments, and remove files without leaving the editor. Full reference: Knowledge & RAG Configuration.

Tab: Assistants

User Access

Whether regular users may reach assistants at all, and whether they may author their own.

Disable Assistants for User

When enabled, regular users cannot access the Assistant Library or use custom assistants. Administrators retain full access. Useful when the twin should present a single unified persona rather than a menu of specialists.

Disable Create Assistants for User

When enabled, regular users can use assistants but cannot create new ones. All assistants are admin-authored — useful for curated deployments (curriculum, customer support).

Enable Assistants for Email

Whitelist of email addresses allowed to use assistants when assistants are otherwise disabled. Useful for granting authoring access to a small pilot group.

Available Assistants

A multi-select of specific assistants to hide from the library on this instance, even if they exist in the catalog. Use this to retire an assistant without deleting it. Full reference: Assistants.

Tab: Agents

Provision and manage autonomous agent workspaces for this Digital Twin — workspace status, scheduled heartbeat tasks, live sessions, and the approval queue.

This tab appears only when Autonomous Agent is enabled under Configuration → Autonomous Agent, which is a super-admin setting.

Full reference: Agents.

Tab: Twin Memory

Twin Memory is the umbrella for what the twin knows about a person across conversations. It has two parts, each with its own section.

Long-term Memory

What the twin forms on its own from conversations, with a visible receipt for every memory it saves. Controls here decide whether it is available on this instance, whether it is limited to administrators, and whether memories may be shared across sibling twins. Display Memory Details (on by default) controls whether the expandable Memory row under an answer lists the memories that were Recalled to shape the reply. Turn it off for a quieter transcript — memories are still used, they are just not listed. Anything the twin Saved, Updated or Forgotten during the exchange is always shown in the same row, so a user can always see what was kept. The same controls are also available to instance administrators from inside the product, in Instance Settings → Knowledge → Long-term Memory (the first card of that tab). Turning the feature on or off and account-wide sharing remain platform-administrator actions and show as read-only there for other admins.

Shared Memory

Facts the whole instance reads — set once by an administrator and available to every user of this Digital Twin. Full reference: Twin Memory and Memory Parameters & Act As.

Knowledge & RAG Configuration — Retrieval modes, chunk handling, embeddings, KAG analysis model, upload policies
Realtime Voice & Avatars — Provider catalog, voice tuning, avatar configuration
Cloud Services — Google Workspace, Microsoft, and Kaltura setup
MCP Servers — Inbound and outbound Model Context Protocol setup
Twin Memory — Long-term Memory and Shared Memory
Memory & Act As — Per-user memory, shared memory, impersonation
AI Models — Provider catalogs, BYOM, reasoning effort, prompt caching
Personalization — Identity, avatar, branding, model assignments
Content Moderation — Per-message safety screening
Agents — Autonomous agent workspaces, scheduled tasks, approvals
Meeting Agent — Sending the twin into a Zoom, Meet, or Teams call
Credit Management — Pooled credits, user quotas, and caps
Onboarding Questions — Guided personalization for new users