CLI use case
CLI for coding agents in ops.
A dry run before it changes anything.
The use case
Safe writes.
A dry run before it changes anything.
The same typed tools can also serve an MCP server for ChatGPT and Claude.
What Flow handles
The product work, not the plumbing.
- Each tool is a command with flags from its typed input, JSON output and help text from its description.
- Ship a feature once; it lands in the CLI, in ChatGPT and in Claude together.
- Scenario tests with simulated users, and every call traced.
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 CLI.
Start with the product page, then ship the same agent and tools wherever your customers use them.