Let agents find US doctors with checkable evidence over MCP
A developer built a remote MCP server with 1.2M US physicians, Medicare procedure volumes and facts from hospital sites.
Get your rental deposit back with a researched demand letter
A San Francisco renter used ChatGPT and Gemini to research tenant law and write a demand letter; the landlord returned $4,200 of a $5,000 deposit.
- Difficulty
- BeginnerOur rating
- Time to build
- 1-2 hours (sourced)From the source
- Monthly cost
- Not reported
- Revenue
- Not reportedWe only show revenue the source states
- Engagement
- No public countThe source shows no number
What they did
The models helped identify violations of California tenant law and draft the letter.
How it went
The renter got $4,200 back, about 1-2 hours of work.
Worth knowing
This is not legal advice; check the statutes cited.
Builder recipe
Our own starting point, written from the source. Adapt it to your setup.
Stack
- ChatGPT
- Gemini
Steps
- Collect the documents.
- Have the agent extract and summarize.
- Have a qualified person review.
- Store the result securely.
Starter prompt
My landlord kept $X of my deposit in [city/state]. Explain the deposit rules with citations, list what they did wrong, and draft a firm demand letter.Tags
Read the original
Related use cases
Render videos from a short JSON your agent writes
A developer open-sourced Lampo, which renders video from agent-written JSON without a browser, about 4x faster than headless Chrome.
Run SEO audits from your coding agent with local math
A developer built an SEO system with 85 skills and 29 agents that runs in Claude Code, Gemini CLI and Antigravity.
Generate LEGO models from a prompt
A hobbyist spent months getting ChatGPT and Claude to write LDraw, the instruction language for LEGO CAD models, and open-sourced the tooling.
The Daily 5.
Five real AI agent use cases each morning, each with a recipe and a source. Plus a Sunday roundup. Free.