Input and Responses

Talk to your Digital Twin — typing, dictation, voice mode, and what you can do with each response.

The input pill at the bottom of your screen is where every conversation happens. It hosts four interaction surfaces:

Surface	Where it lives	What it does
Text input	Centre of the pill	Type a question or instruction
[+] action menu	Left edge of the pill	Files, Assistants, Knowledge, Audio, Settings, More
Convo button	Right of the pill	Toggle hands-free speech-to-speech voice mode
🎙 Mic button	Next to Convo	Open the dictation recorder (transcribe a message into the textarea)

A Submit button replaces Convo on the right whenever the textarea has content; press Enter or click it to send.

---

Typing prompts

1. Type your question

   Click into the textarea and write your prompt. The pill auto-grows from a single line into a multi-line editor as you type.

   Prompt

   Summarise the attached vendor agreements and highlight any renewal-fee surprises.
   
2. Submit

   Press Enter to send, or Shift + Enter to add a newline without sending. The Convo button is hidden while the textarea has content; a green Submit button takes its place.

3. Response streams in

   Pria streams the answer token-by-token. 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.

---

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.

New Conversation

Start a fresh conversation thread. Optionally pick an assistant first — the new conversation will be scoped to that assistant’s instructions, tools, and Knowledge configuration.

Files / Attachments

Attach files for the next turn or browse what’s already in your IP Vault. Audio Notes and document uploads land here. Confidential files can be marked so they’re answered against but never quoted verbatim.

Assistants

Switch the assistant for the next message only, or open the Assistants gallery to manage / favorite / publish your own.

Knowledge

Two channels of context that Pria can pull from:

• Memory — long-term facts Pria remembers about you across sessions (your role, ongoing projects, preferences). Opens the Memory Parameters Lightbox.
• Sources — three mutually-exclusive retrieval modes, plus an orthogonal Search Only checkbox.

Retrieval Mode (radio):

Mode	What runs
Disabled	No retrieval. The LLM answers from its training only.
RAG Only	Dense vector retrieval over your vaults + LLM rewrite. The default.
RAG + KAG Fusion	Dense vector + knowledge-graph retrieval, fused via Reciprocal Rank Fusion. Best for complex queries where rephrasing matters. KAG is always an augmentation on top of RAG — there is no “KAG without RAG” mode.

Search Only (checkbox, orthogonal): when on, Pria returns the raw matching vault chunks instead of an LLM-rewritten answer. Useful for debugging retrieval coverage or exporting raw evidence. Greyed out when retrieval is Disabled.

A small coloured badge appears next to the Knowledge label whenever you’re in a non-default state: red for Disabled, amber for Search Only, blue for RAG + KAG.

Search Conversations

Search inside the active conversation (highlights matches inline) or expand the query across every Digital Twin you can access.

Audio

Two audio-related toggles:

• Speech to Text (checkbox) — shows the dictation 🎙 mic in the input pill. When off, the mic is hidden.
• Text to Speech — Voices — opens the browser voice picker so you can choose how Pria’s responses sound when read aloud.

Settings

Quick links into the two settings Lightboxes:

• Personal — opens Your Profile (General, Personalization, Knowledge, Your Data, Security, Google Cloud, Canvas/LTI, Billing, Developer/API).
• Instance — admins only. Model picker, RAG / KAG, Voice, Tools, Assistants, Invite, Billing for the current Digital Twin.

More

• User Guide / Admin Guide — opens docs.praxis-ai.com in a new tab.
• Feedback — file a bug or feature request.
• Referral — open the Referral Program Lightbox to earn credits for inviting others.

The menu footer carries two quick-zoom controls — Smaller and Larger — that scale the entire UI.

---

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 a single shot to your institution’s configured speech-to-text engine (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. No Upload, no History, no embeddings. The audio 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.

• Default model: OpenAI’s gpt-realtime-2 (configurable per institution; Gemini Live and xAI 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, generate images, query Canvas, etc., while you talk to it.

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 real-time bidirectional audio session; the mic is a one-shot transcribe-then-type. 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 — 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) to have the streamed response read aloud using the voice you picked under Audio → Text to Speech — Voices.
• Start typing the next prompt — your input queues and submits as soon as the current response finishes.

---

What you can do with a completed response

Hover any past dialogue (input + response pair) to reveal its action row:

Share as link

Generate a public shareable URL of this conversation. Recipients can read the dialogue without an account — useful for sending insights to colleagues or saving for later reference.

View Details

Open the per-dialogue info card. Shows timestamps, the model used, token counts (input / completion / Thinking for reasoning models), tool invocations, and the parent conversation context. Also gives you a Print option.

Delete dialogue

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.

Copy input / Copy output

Two separate buttons. Copy the original prompt for re-use, or copy Pria’s full response (with formatting preserved where possible) into another app.

Add to / Remove from Favorites

Click the ⭐ to bookmark a useful response. Bookmarked dialogues show up under Favorites in the sidebar so you can jump back any time.

Read aloud (TTS)

Have Pria’s response spoken using the voice you chose in Audio → Text to Speech — Voices. The voices come from your browser’s built-in speech-synthesis engine, so the catalogue varies by OS.

Citations

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.

Thinking Tokens — when the active model is a reasoning model (OpenAI Responses API, Gemini 2.5+, gpt-realtime-2), the View Details card shows a separate “Thinking” token count alongside the visible completion tokens. This is the reasoning the model did before answering, billed and tracked separately.