At the top of my AGENTS.md:
- NEVER write unit tests after you write code.
- Highly prefer E2E tests as the sole testing mechanism. Use them to verify complex features work. At the end of E2E tests, produce a verifiable and repeatable artifact.
- If you must test a system in isolation, FIRST write all the ways it could fail, THEN write the code.
I can’t believe I have to manually switch
- model
- model tiers
- reasoning level
- effort level
- speed
We have an all powerful AI but still need to click through 10 menu to configure it.
Unbelievable.