Settings

Documentation Index

Fetch the complete documentation index at: https://isaree-cd4b6397.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Settings is where everything that shapes Isa’s behavior lives — the Primary Agent, the prompts that guide the Primary Agent in Patient Chat, and the Scribe Agent routing.

​

Pick the Primary Agent Model

Open Primary Agent Model to choose which model the Primary Agent uses in Patient Chat. The picker has its own page — see Primary Agent for on-device versus cloud, the model families, and Thinking Mode.

​

Edit the system prompt

Open System Prompt to bring up the Primary System Prompt sheet. Edit and save in place — the prompt is stored on this device and doesn’t sync between devices. For what the system prompt does and how it differs from an Agent’s prompt, see Primary Agent → Edit the system prompt.

​

Edit the summarisation prompt

Open Summarisation Prompt — same editable sheet pattern. The summarisation prompt controls how Isa compacts older Patient Chat turns once the context window fills up. The default is a structured clinical template — patient line, active problems, history, findings, assessment, plan, open questions, clinician preferences — followed by rules like “use only facts stated in the conversation” and “prefix uncertain facts with ?”. Your version takes effect on the next compaction.

​

Pick the extraction provider

Open Extraction to pick where the Scribe Agent’s extraction step runs.

• On-Device — extraction uses the Primary Agent’s loaded on-device model. No API key required.
• OpenAI — extraction runs against an OpenAI model. Paste your OpenAI API key when prompted; the key is saved on this device with the last four characters shown.

The Extraction provider is independent of the Primary Agent’s own model — the Scribe extraction step can land on a different provider than the conversational Primary Agent.

​

Pick the transcription provider

Open Transcription to pick where Scribe transcription runs.

• ElevenLabs — transcription and diarization run via ElevenLabs. Paste your ElevenLabs API key when prompted; the key is saved on this device.
• On-Device — transcription uses the bundled ASR model and diarization model. No API key required.

​

Next