What each prompt includes
Prompts do not include credentials. Get your Partner ID, register your JWKS, and confirm template IDs through Partner onboarding before you run generated code.
How to use these prompts
- Choose the workflow, SDK, or API you are integrating.
- Copy the prompt, or open it in Cursor from the prompt actions.
- Paste it into your agent chat, and add details about your stack (language, framework, EHR) on the line after the prompt.
- Review anything the agent marks as BLOCKED or Not run before you ship.
Choose a workflow
Use a workflow prompt when you know the job (Ambient notes, Form filling, Dictation) but have not chosen between an SDK and the Partner APIs. The agent loads the workflow skill, which routes to the right SDK or API skill.- Ambient
- Form Filling
- Dictation
- Patient Summary
- Audio Streaming
- Webhooks
Load the Ambient skill, build against staging, and stop at a retrieved note.
Choose your SDK
Use an SDK prompt when you have already chosen the SDK. Each prompt names the option that points the SDK at staging.- Web SDK
- Headless Web SDK
- Mobile SDK
- Dictation SDK
- Form Filling SDK
Load the Web SDK skill, set the staging environment, and run an Ambient session end to end.
Choose your API
Use an API prompt when you call the Partner APIs directly. Each prompt points the agent at the public OpenAPI spec so it can check request and response shapes.- Ambient API
- Form Filling API
- Dictation API
- Patient Summary API
Load the Ambient API skill, call staging, and stop at retrieved note content.