2 Comments
User's avatar
Mohamed F. Ahmed's avatar

We tried a version of this at a portfolio company last year, three agents shipping in parallel with automated test gates and zero human review pre-merge. It fell apart in about two weeks, not because the code was bad but because nobody could reconstruct why a decision was made when something broke downstream. The bottleneck moved from writing code to explaining it.

Jina Yoon's avatar

Very similar to Dex's experience!