HACKER Q&A
📣 logicallee

How did you scale AI development?


I have a medium sized project AI is developing with some guidance from me. (This is the only way I can put it, since I don't have expertise in the technologies it's using, it's like I'm managing its development.)

As I develop it, I run into regressions where previously working features become broken. I'd like to keep iterating on it this way, since I have built perfectly working applications with AI. Do you have any tips for me? How did you successfully scale developing with AI?

  👤 janpio Accepted Answer ✓
Is the breaking functionality fully covered with tests, and the agent can and does run those tests when adding or changing things already? If not, that would be a promising approach to help the AI to not mess up. If yes, can that loop be further tightened to support the AI?