Skip to main content
The rounded bar at the bottom of the screen is where you talk to your Digital Twin — these docs call it the input pill. It holds four things: A Submit button replaces Convo on the right whenever you’ve typed something; press Enter or click it to send.

​
Typing prompts

The Pria text input pill containing a two-line prompt, with the [+] action menu button on the left and the round Submit (send) button on the right.

The input pill: type in the center, [+] action menu on the left, Submit on the right. It auto-grows into a multi-line editor as you type.

1

Type your question

Click into the box and write your message (a prompt). The pill auto-grows from a single line into a multi-line editor as you type.
Prompt
2

Submit

Press Enter to send, or Shift + Enter to add a newline without sending. The Convo button is hidden while you have text typed; a round Submit (↑) button takes its place.
3

Response streams in

Pria writes the answer out as it goes, a few words at a time. You can keep typing your next prompt while the current one streams — they’ll queue.
Be specific. Pria responds better to focused questions (“Compare clauses 4.2 and 7.1 of the attached MSA”) than to vague ones (“Tell me about this”). When you don’t get what you want, refine the prompt rather than starting fresh — Pria has the recent conversation in context.

​
Keyboard navigation through prompt history

The input pill remembers everything you’ve sent in the active conversation. When the box is empty, you can scroll back through your previous prompts without leaving the keyboard: Drafts are preserved. If you’d started typing a new prompt and then pressed ↑ to look at an older one, your in-progress draft is held aside. Walking forward past the newest history entry with ↓ drops you back into the draft exactly where you left it — nothing typed is lost while you browse. History navigation only activates when the cursor is at the very start of the box, so multi-line editing with arrow keys still works as expected inside a prompt.

​
Re-asking and editing the last question

Two quick ways to retry a turn without re-typing:
  • Edit and resend the last prompt — press ↑ once in an empty box. Your most recent message reloads; tweak the wording and press Enter to send the new version. This creates a fresh turn — the original stays in history.
  • Regenerate from the same prompt — hover the last response and use Copy input → paste → send if you want to retry verbatim, or open the dialogue’s action row and use Delete dialogue first if you want the old answer out of context before re-asking.
Editing the prompt and resending is usually better than asking “no, try again” — Pria sees both the new prompt and the unhelpful previous answer in context, and tends to overcorrect rather than start clean.

​
Pasting images and drag-dropping files

The input pill accepts files three ways without ever opening the [+] menu:
  • Drag and drop — drag one or more files from your desktop onto the input pill (or anywhere over the conversation surface). A blue overlay highlights the drop zone; release to start the upload.
  • Paste from clipboard — copy an image (screenshot, browser image, etc.) and press Ctrl/⌘ + V with the cursor in the box. Images paste as attachments; text pastes inline.
  • Browser file picker — open [+] → Add Photos & Files to browse your vault, or tap the row’s right-edge + to jump straight to your computer’s file picker.
The Pria drag-and-drop overlay: a dashed blue border around the conversation with a download icon and the prompt 'Drop files to upload into your Vault'.

Drag files anywhere over the conversation and a blue drop zone appears — release to upload into your Vault.

However you add them, files open the Add to your personal IP Vault uploader — with Files / URL / Clipboard tabs, a per-file Skip Indexing toggle (store the file without making it searchable — for something you only want Pria to look at this once), and an Upload button. Uploaded files attach to the next turn and also land in your IP Vault (My Files) for re-use.
The Add to your personal IP Vault uploader widget showing Files / URL / Clipboard tabs, a queued file with its size and a Skip Indexing checkbox, and a green Upload button with size limits below.

The file uploader: review the file, optionally Skip Indexing, then Upload to your personal IP Vault.

Models that can see images can work directly from a pasted picture — paste a screenshot of an error message, a chart, or a whiteboard photo and ask Pria what’s in it.

​
Quoting a prior message

To reference an earlier message in your follow-up without retyping it:
  1. Hover the message you want to quote and use Copy input or Copy output from the dialogue action row.
  2. Paste into the box — Pria’s markdown preview renders the quoted block as you type.
  3. Add your follow-up question beneath the quoted block and send.
Even without explicit quoting, Pria has the most recent dialogues in context (see Remember History) — so references like “the second bullet you mentioned above” generally resolve fine for nearby turns.

​
Which model answers

There is no model picker in the message box. In a Digital Twin, its administrator chooses the model in Instance Settings → Conversation, and an assistant can use its own model. Your personal Pria (your own account, outside any Digital Twin) uses Pria’s default model, which you can’t change. If you need a different model, ask the Digital Twin’s administrator. See AI Models for Your Twin.

​
Markdown formatting in responses

Pria streams answers as Markdown. The renderer supports:
  • Headings, bold, italic, lists, blockquotes — standard CommonMark. Bulleted lists show bullets (•, then ◦ and ▪ for lists inside lists); a list inside a numbered list counts i, ii, iii, then a, b, c.
  • Code blocks with syntax highlighting — triple-backtick fences with a language tag (```python, ```ts, etc.). Each block carries a Copy button.
  • Tables — pipe syntax renders as a clean grid. Long tables scroll horizontally inside the response.
  • Inline links — clickable, open in a new tab.
  • Math — inline $E = mc^2$ and block $$ … $$ render via LaTeX-style markup when the active model emits it.
  • Mermaid diagrams — flowcharts, sequence diagrams, gantt, etc. inside ```mermaid fences render as SVG.
  • Citations — clickable chips after sentences that reference your IP Vault content.
A Pria response rendered as a numbered list with the key phrase of each item shown in bold.

Pria renders answers as Markdown — headings, bold, lists, tables, code, math, and more.

Code blocks remember language across turns — Pria tends to keep replying in the same code style you’ve been working in.

​
Wide conversation

On a tablet or computer, the Wide conversation button (two arrows pointing outward) at the top right of the conversation lets it use the full width of the screen — handy for wide tables and code. Select it again for the usual centred width. Pria remembers your choice, in the Studio UI too.

​
The [+] action menu

Click the [+] icon on the left of the pill to open a structured menu of everything you can attach to or change about the next turn. Each entry that has more options expands inline when you click it — its choices appear indented just below the row, rather than flying out to the side.
The Pria input action menu showing Files, New Conversation, Assistants, Search, Knowledge, Personal Settings, Audio, and More, with Smaller / About / Larger controls pinned in the footer.

The [+] action menu, expanded above the input pill.

“About this menu” — built-in help on tap. Every expandable submenu carries a small ? About this menu link pinned at the bottom of its options. The help text stays hidden until you click it (it then changes to Hide info), so the menu opens clean and uncluttered. If you’re ever unsure what a section does, expand it and tap ? About this menu for a plain-English explanation.
Start a fresh conversation thread. The submenu lists your favorite assistants as one-tap shortcuts, plus Select Assistant… to browse them all — the new conversation is scoped to whichever assistant you pick (its instructions, tools, and Knowledge configuration).
The New Conversation submenu opened from the [+] action menu, listing favorite assistants and a Select Assistant option.

Starting a new conversation from the [+] menu — favorite assistants appear as one-tap shortcuts.

Attach files for the next turn or browse what’s already in your IP Vault. The row’s right-edge + is a shortcut that opens your computer’s file picker directly, skipping the vault browser. Audio Notes and document uploads land in your vault. Files in shared vaults can be marked Confidential — their knowledge still informs answers, but only the owner can open them or see their details.
Manage your assistants, quick-edit the one you’re currently using, create a new one, or switch the assistant for just the next message using the inline type-to-filter picker. The current assistant is highlighted with a Current badge; pick a different one to queue a one-message override (a chip shows the pending switch next to the input).
Search inside the active conversation (matches are highlighted inline). If you belong to more than one Digital Twin, the submenu also offers Search Across All Digital Twins to widen the query to every twin you can access. On a personal account with a single twin, Search is a single one-tap entry instead of a submenu.
The Search entry in the [+] action menu, with the option to search the active conversation or across all Digital Twins.

The Search option in the [+] action menu.

Three things that shape what Pria draws on when it answers:
  • Remember History — a quick selector for how many recent exchanges stay in context (0 disables history; higher keeps more, at higher credit cost; deep settings auto-summarize to save credits). The slider is in Your Profile → Personalization.
  • Memory — Enable User Memory (whether Pria remembers facts about you across conversations), Enable Long-term Memory where your Digital Twin offers it, and Manage Memory… to see and edit what was saved.
  • File Vault — whether and how Pria reads your files: a retrieval mode, plus a separate Search Only switch.
Retrieval Mode:Search Only (a separate switch): when on, Pria returns the matching passages from your files as they are, with no AI-written answer on top. Useful for seeing exactly what your documents say, or for collecting raw evidence. Only shown while retrieval is on.A small coloured label next to Knowledge shows the current mode when it isn’t plain RAG: Disabled (red — your files are switched off), Search Only (amber — raw passages instead of a written answer) or RAG + KAG (blue — the knowledge-graph search is on).
Choose which tools the AI may use. On a personal account the row shows your current set and count (for example Minimal - 6 on) and opens your own picker, with the Tools Guidance switch under the list. If you can edit the Digital Twin, it reads For everyone in this Digital Twin - 12 on and sets the tools for every member. Members who can’t edit the twin don’t see the entry — the twin decides. See Choosing Your Tools.
Appears only when an administrator has made subagents available. Opt in for yourself and choose how much of a team the twin may bring in — see Single Model vs Agent Mode.
The Settings row uses the same dials icon as the sidebar Settings tab. It links into the two settings areas:
  • Personal (Yours) — opens Your Profile (General, Personalization, Knowledge, Memory, Your Data, Security, Google Cloud, Microsoft 365, Canvas / LTI, Billing, Developer / API — the integration tabs appear when your organization enables them).
  • This Digital Twin — admins only; labeled with the twin’s name. Opens the Instance Settings panel (General, Personalization, Conversation, Voice, Knowledge, Tools, Assistants, Subagents, Connectors, Quotas, Invite, Integration, Billing). A right-edge open-in-new icon jumps to the full admin Edit Digital Twin page. Members who can’t edit the Digital Twin see a single Personal Settings entry instead.
Voice-related controls:
  • New Audio Note — record a voice note and add it to your knowledge (shown when audio notes are available).
  • Speech to Text (toggle) — shows the dictation 🎙 mic in the input pill. When off, the mic is hidden.
  • Read Aloud — Natural Voice (toggle) — read responses with the speech model. Where this is managed depends on your account: Instance Settings → Voice for admins, Your Profile → Personalization for personal accounts, or set by your Digital Twin admin for members.
  • Text to Speech — Voices — pick the voice used to read responses aloud (the browser voice picker, or your settings page when the natural voice is on).
  • User Guide / Admin Guide — opens docs.praxis-ai.com in a new tab (Admin Guide shows for admins).
  • Privacy Policy — read your organization’s privacy policy again (shown when it has one).
  • Feedback — file a bug or feature request.
  • Referral — open the Referral Program Lightbox to earn credits for inviting others.
The menu footer carries three quick controls — Smaller, About, and Larger. Smaller and Larger scale the whole conversation — your messages, the replies, the typing area, and the interface — and keep the menu open so you can zoom repeatedly. Your choice is remembered between visits, and Pria also respects the text size set in your browser’s own accessibility settings. About opens the Pria walkthrough.

​
Voice dictation

The 🎙 mic button on the right of the pill opens an in-place audio recorder (when Audio → Speech to Text is on in the [+] menu).
1

Tap the mic

The textarea is replaced in-place by a recorder widget showing a pulsing red dot, an MM:SS timer, a live waveform of your voice, and Cancel / Confirm buttons.The first time, your browser will ask for microphone permission. Pick Allow while visiting the site to remember it.
2

Speak your message

Recording is capped at 2 minutes with a 10-second warning before the cap. The waveform animates in real time so you can see Pria is hearing you.
3

Confirm

Click Confirm to transcribe. The audio is sent in one go to the speech-to-text service your Digital Twin is set up with (Voxtral, Whisper, etc.) — the same one used by Audio Notes and Convo mode. The transcript is appended to whatever text you’ve already typed, so you can dictate part of a message and finish typing.
Nothing is stored after transcription. The recording isn’t saved as a file, isn’t added to your history and isn’t indexed — it is processed and discarded.
Click Cancel at any time to discard the recording.

​
Convo mode (speech-to-speech voice)

The Convo button on the right of the pill launches a hands-free voice conversation with Pria. Click once to start, click again to stop.
The Pria Convo mode widget — a circular animated avatar with a START button, a resize control, and a voice selector (e.g. Cedar), floating over the conversation.

The Convo widget: press START to begin a hands-free voice session, pick a voice, and drag or resize the floating panel.

  • Voice provider: chosen by your Digital Twin’s administrator — OpenAI’s realtime model by default; Gemini Live, xAI, ElevenLabs, Cartesia and the Anam avatar are also supported.
  • Live transcript: a character-by-character transcript appears under the voice indicator as you and Pria speak.
  • Tools work in voice: Pria can search your vault, look things up and call the services it is connected to while you talk. Tools that only make sense in writing sit out a spoken turn.
You can drag the Convo widget anywhere on the screen and resize it. Closing the widget ends the voice session.
Convo mode and the 🎙 mic dictation are independent. Convo is a live two-way voice call; the mic records once, turns it into text, and stops. Use Convo for back-and-forth conversation; use the mic when you want to compose a single longer message hands-free.

​
While a response is streaming

You can:
  • Stop the response with the Stop button (labeled Abort in the control row) — anything generated so far is preserved.
  • Pause auto-scroll so you can read at your own pace while the rest streams in below.
  • Enable audio (TTS) with Speak to have the streamed response read aloud using the voice shown beside the controls (set under Audio → Text to Speech — Voices).
  • Start typing the next prompt — your input queues and submits as soon as the current response finishes.
Duplicates are caught. If the same question is accidentally sent again while the first submission is still working (a double-click, a reflexive retry after a slow turn), Pria recognizes it and points you back to the answer already in progress instead of starting — and billing — a second run.
A response streaming in token-by-token, with Stop/Abort, Streaming, and Speak controls and the selected text-to-speech voice shown beneath the answer.

While a response streams, the control row offers Stop (Abort), pause, and Read Aloud (Speak).

​
What you can do with a completed response

Hover any past dialogue (input + response pair) to reveal its action row:
The action row beneath a completed Pria response: Copy input, Copy output, Share as link, View details, Delete dialogue, and Read aloud, with thumbs up / down and a favorite star at the top-right.

Hovering a completed dialogue reveals its action row.

Open the Conversation History card — a per-dialogue summary that reveals how Pria processed the turn:
  • Secure Link — a shareable URL for this dialogue (the same link as Share as link).
  • Details — the user and the Digital Twin the turn ran on.
  • Conversation — the full input + response transcript.
  • Performance — the Created timestamp, RAG Search time, Exec. Duration (total processing time), and TTFT (time to first token — how long before the model started streaming).
  • Model — the exact model that answered, and the Credits the turn consumed.
A Print button exports the card. It’s the quickest way to see which model ran, how long retrieval and generation took, and what the turn cost.
The Conversation History detail card: Secure Link, Details, the conversation transcript, a Performance section with Created, RAG Search, Exec. Duration and TTFT, and the model used with its credit cost.

The View Details card surfaces the model, performance timings, and credit cost behind a single response.

The chart icon toggles an inline usage card right under the response — a tabbed breakdown of what the turn used:
  • Overview — total tokens, credits, duration, tool calls, time to first token, and retrieval timing at a glance.
  • Pricing — the itemized bill on one table: every model involved, its tokens, and its credits. When the turn ran an agent team, the manager and each helper get their own row, and the total is what was billed.
  • Tokens / Context — where the tokens went, and how much of the model’s working memory (its context window) the turn used. Context appears when that breakdown is available.
  • Retrieval — appears when the turn searched your vault; shows what was retrieved.
It’s the quickest way to understand what a single answer cost and why. See Credits for how the numbers translate to your balance.When an answer stopped early, the card says so in a line such as Cut off after 20/20 tool calls. It means the reply reached the limit on how much looking-up one answer may do, or how long it may run, and wrote its answer from what it had gathered. Ask it to continue and it picks up from there.
Permanently remove this dialogue from history. Cannot be undone. Use it to clean up stray turns or remove sensitive content you don’t want to keep.
Two separate buttons. Copy the original prompt for re-use, or copy Pria’s full response (with formatting preserved where possible) into another app.
Click the ⭐ to bookmark a useful response. Bookmarked dialogues show up under Favorites in the sidebar so you can jump back any time.
Have Pria’s response spoken using the voice you chose in Audio → Text to Speech — Voices. With Read Aloud — Natural Voice on, responses are read with a natural AI speech model; otherwise the voices come from your browser’s built-in speech-synthesis engine, so the catalog varies by OS.
When Pria’s answer drew on documents from your IP Vault, citation chips appear inline. Click one to open the source file in the Files preview, with the matching chunk highlighted.
Reading the performance numbers — TTFT (time to first token) is how long you waited before the answer started appearing; Exec. Duration is the full turn including any tool calls; RAG Search is how long the file search took. The Credits figure is what the turn cost. Some AI models work through a problem privately before they answer — you don’t see that work, but it takes time and costs credits, which is why a short answer can still be an expensive one. See Reasoning & Thinking for how that effort is configured.