Results

2 stories for“Use tests, benchmarks or review evidence as feedback.”

Loop Engineering Is the New Skill Behind Better AI Coding

Claude Code lead Boris Cherny's shift from writing prompts to designing loops points to a more disciplined way of building reliable software with agents.

Jul 27, 2026

Technology

Code Review After AI: Smaller Diffs, Better Evidence, More Judgment

As agents generate more implementation, review quality depends on keeping changes small, showing verification and protecting the human attention budget.

Jul 27, 2026