Uncle Bob says agentic coding works best when agents are boxed in by tests
ecsquendor · x · 2026-07-26
A developer argues that the key to agentic engineering is to extract as many interactive constraints from humans as possible.
In the quoted thread, Uncle Bob says he no longer reads the code written by his agents directly. Instead, he surrounds them with strong constraints — unit tests, Gherkin tests, QA procedures, quality metrics, mutation testing, coverage, and more — so the agents have to pass a rigorous gauntlet before the code is trusted.
More from coding & agent
- CREAO schedules a July 30 panel on getting AI from demo to production — thetripathi58 · 2026-07-26
- An AI agent clears Slay the Spire 2 on Ascension 8 and opens its harness and trajectories — bdsqlsz · 2026-07-26
- MemGym benchmarks long-horizon memory for LLM agents across coding and web tasks — dhruv2038 · 2026-07-26
- Developer says $5 a month bought 339.8 hours of agent sandbox compute — aniketmaurya · 2026-07-26
- The loop makes the model attack its own proof until no flaw remains — FinanceYF5 · 2026-07-26
- Codex ran for up to 32 hours on some of the math problems — FinanceYF5 · 2026-07-26