How do you guys trust AI enough to ship without checking what it built?
I'm running 5 to 8 agents in parallel, but I still need to check the final output before pushing to prod.
I know there are workflows and tools to automate this, but I can't seem to let go yet
Anyone else struggling with this or am I just slow to adapt?
commit 52f163a
Lots of rules and tests and I still check before pushing, but most of the time it looks good.
I make sure tests are written and have 100% coverage and I often (but not always... depends) run
/code-review (both the Anthropic one and the one from Matt Pocock to make sure it matches all my .ai/rules)I ignore the code, but I test that the end-user experience is what I expect it to be. I managed teams of engineers, and this is no different, except when AI writes the code, AI can also fix the code, so not worried about syntax and function naming. No need for pair review.
(when…