Organize your personal medical records with an AI assistant
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Use cases
Show all 6Show fewer
Methods
Collect your records in one local folder, open it in Claude Code or Codex, and have the assistant file facts while the originals stay untouched
Steps
- Create a folder, for example `my-health`. Inside it, create `original-records/` and copy every medical file you have into it: PDFs, photos of documents, screenshots, portal exports. Any order, any shape. Nothing in there gets edited.
- Read the [privacy and safety guide](02-privacy-and-safety.md). Check device encryption, backups, and your provider's training and retention settings.
- Open `my-health` as a local folder in [Claude Code](https://claude.com/claude-code) or [Codex](https://openai.com/codex). These are coding assistants that can see files on your computer. You talk to them in plain language.
- Paste this prompt:
- > Read https://github.com/dariaminsky/ai-patient-toolkit/blob/main/AGENTS.md and follow it. My originals are in `original-records/`. Explain the data flow before reading any of them. Ask for consent for each batch of files. Show me the file plan first. Keep the originals unchanged. Ask me to verify every extracted date, unit, value, and source.
- If the assistant cannot open links: press the green **Code** button on this page, then **Download ZIP**. Unzip it into `my-health` and point the assistant at `ai-patient-toolkit/AGENTS.md` instead. The `starter/` folder holds the same templates for filling in by hand.
- Review the plan. Approve one step at a time. Start with two or three documents, not the whole archive. Check every extracted fact against the original.
- Use it when you have medical files scattered across PDFs, photos and portal exports. Medical records are sensitive, so check device encryption, backups and your provider's data settings first, and check every extracted value against the original.
- Note: Steps from Daria Minsky's ai-patient-toolkit quick start (CC BY 4.0). Not a substitute for clinical care.
Run this method with your agent
Download .mdCopied 0
--- name: "organize-personal-medical-records-method" description: "Use when you need to Organize your personal medical records with an AI assistant. Collect your records in one local folder, open it in Claude Code or Codex, and have the assistant file facts while the originals stay untouched" --- # Collect your records in one local folder, open it in Claude Code or Codex, and have the assistant file facts while the originals stay untouched Job: [Organize your personal medical records with an AI assistant](https://aiagents.org/canai/organize-personal-medical-records) ## Need - AI agent ## Steps 1. Create a folder, for example `my-health`. Inside it, create `original-records/` and copy every medical file you have into it: PDFs, photos of documents, screenshots, portal exports. Any order, any shape. Nothing in there gets edited. 2. Read the [privacy and safety guide](02-privacy-and-safety.md). Check device encryption, backups, and your provider's training and retention settings. 3. Open `my-health` as a local folder in [Claude Code](https://claude.com/claude-code) or [Codex](https://openai.com/codex). These are coding assistants that can see files on your computer. You talk to them in plain language. 4. Paste this prompt: 5. > Read https://github.com/dariaminsky/ai-patient-toolkit/blob/main/AGENTS.md and follow it. My originals are in `original-records/`. Explain the data flow before reading any of them. Ask for consent for each batch of files. Show me the file plan first. Keep the originals unchanged. Ask me to verify every extracted date, unit, value, and source. 6. If the assistant cannot open links: press the green **Code** button on this page, then **Download ZIP**. Unzip it into `my-health` and point the assistant at `ai-patient-toolkit/AGENTS.md` instead. The `starter/` folder holds the same templates for filling in by hand. 7. Review the plan. Approve one step at a time. Start with two or three documents, not the whole archive. Check every extracted fact against the original. 8. Use it when you have medical files scattered across PDFs, photos and portal exports. Medical records are sensitive, so check device encryption, backups and your provider's data settings first, and check every extracted value against the original. 9. Note: Steps from Daria Minsky's ai-patient-toolkit quick start (CC BY 4.0). Not a substitute for clinical care. ## Credit Method author ai-patient-toolkit (Daria Minsky; CC BY 4.0) Source: https://github.com/dariaminsky/ai-patient-toolkit#quick-start
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/organize-personal-medical-records - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "organize-personal-medical-records",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}