Feedback-loop ceiling

"The quality of your feedback loops influences how good your AI can code. That is the ceiling." — matt-pocock. Without tests/typechecks the AI codes blind; improving loop quality beats blaming the model.

How to raise the ceiling:

• TDD (red-green-refactor) — "absolutely essential"; instrumenting code before writing it makes test-cheating structurally harder than writing implementation-then-tests in layers.
• deep-modules (Ousterhout) — small interface, big functionality, one big test boundary; unwatched AI produces shallow-module sprawl that can't be cleanly test-bounded. His browser video editor wrapped front-to-back in one outside-testable module was "night and day" for AI effectiveness.
• tracer-bullet-slices — vertical slices make feedback arrive in phase 1 instead of after all layers land; AI naturally codes horizontally.
• Gray boxes — design the interfaces, delegate the implementations: keeps the human's mental model of the codebase without reviewing every line.

Corollary he states plainly: "bad code bases make bad agents." The architectural echo of dhh's Basecamp-5 lesson in vibe-coding (unreviewed agent PRs destroyed the architecture) — and the constructive counterpart to ai-removes-the-maintenance-tax.

Source: report