Build a Scribe Agent

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.

This guide walks through building a Scribe Agent end-to-end on the Community Hub. By the end you’ll have a Scribe Agent that you and other clinicians can download to Isa and use from Patient Chat. A Scribe Agent bundles three things into one downloadable package: an ASR model for transcription, an optional diarization model for telling speakers apart, and one or more Extraction Templates that turn the transcript into a structured clinical note. You can build from scratch or duplicate an existing Scribe Agent on the Community Hub and adapt it.

​

Prerequisites

• A Community Hub account
• A clear idea of what the Scribe Agent should produce — the documentation format (e.g. SOAP note, discharge summary, referral letter) and the fields it should fill

​

Open the build form

Sign in to the Community Hub and start a new Scribe Agent from the Build menu in the top navigation. The form opens with the Scribe Agent’s fields ready to fill in.

​

Name your Scribe Agent

Names are how other clinicians find your Scribe Agent in the Isa Hub — prefer something concrete like GP Consultation Scribe over My Scribe Agent.

​

Add a description

The description is what other clinicians read when they find your Scribe Agent in the Isa Hub. One or two sentences on what the Scribe Agent transcribes and what shape of note it produces is enough.

​

Pick a category and add keywords

• Category — Admin or Clinical.
• Keywords — comma-separated tags that help others find your Scribe Agent when searching. Add a few that match the specialty, the documentation format, or the use case (e.g. dermatology, SOAP, follow-up).

​

Pick an ASR model

The ASR model is what turns the audio into text. Open the picker to search by model name or organization — it pulls open-weight models from Hugging Face that can run on Apple hardware. Each result shows the organization, license, downloads, and likes. For guidance on sizing the model to the device, see Choose a model.

​

Pick a diarization model

The diarization model separates the speakers — yours from the patient’s — so the extraction step knows which words came from whom. It’s optional: leave it on None if the consultation is dictation only or if speaker attribution doesn’t matter for your template.

​

Create Extraction Templates

Extraction Templates are where you define the information to be extracted from the conversation. One Scribe Agent can hold several templates, and the clinician picks which one to use before the consultation. A single GP Consultation Scribe could ship with a SOAP note, a referral letter, and a sick note — same transcription, three different structured outputs. Add a template for each shape of note this Scribe Agent should support. Each template has three parts:

• Template name — what shows up when you pick a template in Patient Chat. Use the documentation format the user will recognize (e.g. SOAP Note, Discharge Summary).
• Extraction prompt — the instructions sent to the model that does the extraction. Tell it what role to take, what to look for in the transcript, and how to handle missing information. This is where most of the quality work happens.
• Output schema — the structured fields the extraction fills in. Build it visually by adding one field at a time, or paste a JSON schema directly.

In the visual builder, each field has:

• Field name — the key in the structured output. Use snake_case (chief_complaint, not Chief Complaint).
• Type — String, Number, Integer, Boolean, or Enum.
• Required — tick if the extraction should always include this field.
• Description — a short hint that helps the extraction model decide what belongs in this field.

​

Build the Scribe Agent

Once the required fields — Agent Name, Description, and ASR Model — are filled in, build the Scribe Agent. It now exists on the Community Hub and is ready to download from the Isa Hub.

​

Understand where the pipeline runs

The ASR and diarization models run on the user’s device. Extraction routing is set separately in Isa — the user chooses on-device or cloud via the Extraction setting in Isa Settings. On-device extraction uses the Primary Agent’s loaded model; cloud extraction routes to OpenAI using the user’s own API key. The user can also run transcription and diarization with ElevenLabs (cloud) instead of the on-device models picked here — using their own API key. That switch lives in Isa Settings, not on this form.

​

Next