Uncle Bob says he trusts agents only after tests and constraints, not by reading their code
tokenbender · x · 2026-07-24
- A screenshot of Uncle Bob Martin’s post says he is now older than everyone else and started coding in the late 1960s.
- His current strategy is not to read code written by agents.
- Instead, he wraps agents in strict constraints: unit tests, Gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and more.
- The idea is that if agents must run through a gauntlet of constraints and tests, he can trust the output without micromanaging the generated code.
- In a reply, he says code quality still matters a lot because messy code slows agents down, so he still enforces strong structure and avoids letting them create tangles.
Related event: Uncle Bob Stops Reading AI Code, Trusts Tests and Constraints(10 posts)→
More from coding & agent
- AIE Code Summit 2026 opens applications: 800 seats, keynotes streamed free — trq212 · 2026-10-27
- Decade-long cloud architect: enterprise AI architecture is far more than bolting on an LLM — kashifmanzoor · 2026-10-27
- Analysis of thousands of coding sessions: 40-89% of files agents read are never used — rseroter · 2026-10-27
- TRL adds Score Centering, a simple fix for RLHF training instability — lvwerra · 2026-10-27
- Precompute golden answers and match at runtime for exact wording control — colinmcnamara · 2026-10-27
- Dev argues there's still alpha in working with your coding agent interactively — alex_frantic · 2026-10-27