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 Trusts AI Coding Agents Only Through Tests(2 posts)→
More from coding & agent
- Databricks Genie runs as an MCP server inside LangGraph, then ships to Azure ML — Cautious-Meringue554 · 2026-07-24
- PenguinHarness open-sources a TypeScript agent builder that claims $0.02 RAG apps — RepulsiveBad8681 · 2026-07-24
- MCPForge scores public MCP servers on security, compliance, and quality — Competitive_Ad_1228 · 2026-07-24
- Superwall ships WWDC.ai light mode after a Claude agent rewrites the design — JordanMorgan10 · 2026-07-24
- Agent systems now bottleneck on cost, with configs spanning nearly 1,000x — abeirami · 2026-07-24
- How should an MCP app be designed for non-technical users? — sn0wquake · 2026-07-24