My brother (@0xDACA) and I worked on a fun project tonight, inspired by @yoheinakajima : Coding Agent that follows the Test Driven Development (TDD) methodology!
You write the tests - and the agent runs in a loop until it creates the feature properly!
1/6
#buildinpublic
We start with a simple FastAPI app and two tests - one of which will fail (the "echo" endpoint does not exist)
2/6
Then - we run the agent - it does not read the tests, it can just run them and get the output.
On the first try, it created the "echo" endpoint with a POST method - which failed, as the test defined it as a GET:
3/6
It then took the failures and converted the code to use GET instead - which failed again but with a different error*.
*We tried to make it fail on purpose, so in the test, we defined the expected key name of the return value as "message1" and not "message"
4/6
It, therefore, took the failures (again), and adjusted the code - this time making the return value "message1" - which worked, and the tests passed.
5/6
Currently only works well with small changes, but we are working on cool stuff for it: enabling changes across multiple files, creating its own tests, etc
Framing it inside TDD is super useful to steer it in a specific, measurable direction - while keeping it somewhat autonomous
Share this Scrolly Tale with your friends.
A Scrolly Tale is a new way to read Twitter threads with a more visually immersive experience.
Discover more beautiful Scrolly Tales like this.