I’ve been using Cursor and other AI coding tools, and I noticed a pattern: they go from requirements → code → fix when it breaks. It works, but it’s reactive. I write what I want, it half-understands, breaks something, and I patch it.
What I wish existed is a flow like this: Requirements → Generate Tests → Generate Code → Run Tests
Basically, AI-assisted TDD. The idea is: * You write requirements in plain English. * The tool turns them into unit/integration tests. * Then generates code that tries to pass those tests. * Then runs the tests and gives feedback.
I’m thinking of building this as a VSCode extension, with a backend (MCP-style) to orchestrate the steps. Cursor would still do the coding part — I just want to slot in before and after to automate testing from the start.
Would you use something like this? Would you pay for it (e.g. Cursor-level pricing, ~$20/mo)? What would break this in your workflow?
.png)

