Make the care plan · Cheatcode

What are you preparing for?

One line is enough. Step 1 asks the rest in your AI app, and nothing is done until you approve the brief it writes.

In the case folder's materials/: Anything about the situation, with other people's names left out.

The person does the work live; the harness prepares and debriefs. Not found and out of scope are valid answers here: it says so instead of guessing.

How the field does this well: Draft, verify every sentence against the source it came from, then a clinician signs.
Keep planned apart from done and symptom apart from diagnosis.
Never decide diagnosis, orders or coding; prepare them for the clinician or coder.
Strip identifiers that are not needed for the task.
Ground it first: Ask for, or look in materials/ for: the clinic's templates, the policies that apply, and the source documents. If there is none, say plainly that the result rests on general defaults, and name them.
What stays with the person: Diagnosis, orders, coding, and the signature on every note. Prepare these; never decide them.
The check that makes it trustworthy: Every sentence traces to its source and nothing enters a record unsigned.
The person's own data: If the person has connected Google Drive / Docs / Sheets, Microsoft 365 (Excel, SharePoint, Teams), read their data through that connector instead of asking for exports, and say which source each number or fact came from. Without one, work from materials/.

On your computer: Your files in materials/, every result in outputs/, the work itself. It runs in your AI app, on the plan you already pay for.
With Cheatcode: The steps, the gates and how far each case has come, so a case survives closing the app. See your cases.