Engineering

Six multi-agent frameworks, measured across coding and reasoning benchmarks. Then the pattern both the loudest sceptic and the loudest proponent ended up agreeing on: many agents may think, one agent writes.

81% of engineering teams report spending more time in code review since adopting AI tools. The advice assumes checking is the cheap half. Measurement says that is where the hours went.

Our AI code reviewer found a SQL injection, described it accurately, and set the verdict to approve in the same response. Here is what we changed.

We planted eight defects in our own CI. Three were caught. One gate was skipping 133,874 of 149,516 links and reporting green. Here is the command that proves it.

A change swapped a made-up number for a confident, wrong explanation of how Propshaft works. Spotting the difference is the thing you are actually hiring for.

TDD looks slow on paper. The real ledger is one hour writing tests against six hours debugging next week. Here is why lightweight TDD wins.

The refactor step breaks more tests than green ever does. Cap each refactor commit at three lines of Ruby and the suite stays green every time.

Solo Claude Code agents ship like solo developers - missing PM, designer, QA, customer voice. Here is the team-mode setup running Shape Up plus XP plus reflection-driven Kaizen.