iMessage use case
iMessage AI agent for dating.
Suggests matches, plans the date and books the table.
The use case
A matchmaker in your texts.
Suggests matches, plans the date and books the table.
The same Flow project can also ship to WhatsApp, Telegram, ChatGPT.
What Flow handles
The product work, not the plumbing.
- You write what the agent can do. Flow handles webhooks, retries, ordering, media and each channel’s formatting.
- Each customer’s conversation is kept between chats, so they can pick up where they left off.
- Scenario tests with simulated users run before every release, and every turn is traced after.
How to begin
A real route to launch.
- 01
Create a Flow project
Run npx @flow-engineer/flow new my-agent, or ask Claude Code or Codex to set it up. You get one folder: the agent’s instructions, its tools, its skills and its tests.
- 02
Write what it can do as tools
Each job is a TypeScript function with a typed input that calls your API: check an order, book a slot, find a deal. No protocol code.
- 03
Test it on simulated users
Run npx @flow-engineer/flow test. Simulated users try the scenarios that matter, including people who change their mind or ask for something your agent should refuse.
One project, more surfaces
Build this on iMessage.
Start with the product page, then ship the same agent and tools wherever your customers use them.