Sandeep Bazar
GitHub
3 posts

lazy-senior-dev

Review personas that ride along inside a coding agent — the lazy-senior-dev project

Agentic AI

Your AI Agent Has Nobody to Answer To. Three Senior Engineers to Break the Loop.

Your agent reviews its own work, agrees with itself, and commits. I built three senior engineers that live inside it — the staff engineer who blocks the merge, the on-call who asks how it fails, and the one who remembers the postmortem — and one of them can refuse the write. Across 2,600 recorded runs on four agents, that refusal is the only thing a better prompt could not replace.

·10 min read
Agentic AI

I Tried to Teach an Agent to Read Git History. It Already Knew.

I built a review persona whose whole claim was that it reads the repository's past — the reverts, the postmortems, the ADR that says don't. Then I measured whether it made any difference. On a strong model it made none: the unaided agent already named the incident in 90% of runs. The useful finding was on the other side of that number, and it changed what I ship.

·8 min read
Agentic AI

Your Coding Agent Already Caught the Bug. That Was Never the Problem.

I gave four AI coding agents the same defective diffs, then made them write the code themselves — 18 tickets, four arms, roughly 800 recorded runs. They caught almost every planted bug unaided. What they could not do was stay quiet about clean code or produce a verdict you could automate on. Three open-source personas, the honest numbers, and the ones that did not work.

·7 min read

← All writing