Uncle Bob says coding agents are only trustworthy when tests and QA box them in
jdjohnson · x · 2026-07-24
Former Stack Overflow co-founder unclebobmartin says his current strategy with coding agents is to not read their code line by line.
Instead, he relies on a thick layer of constraints and verification:
- unit tests
- Gherkin tests
- QA procedures
- quality metrics
- mutation testing
- coverage and related checks
His point is that he can trust agent-generated code only after it runs through a very demanding test gauntlet. That, he argues, is how he captures the agents’ productivity without sacrificing confidence in the output.
More from coding & agent
- Anthropic engineer says teams are moving from prompts to graph-orchestrated self-improving agents — colinmcnamara · 2026-07-24
- Offloop’s multi-agent harness beats Claude Code and Codex on workflow benchmarks — SucceededMind · 2026-07-24
- shadscan brings deterministic UI audits to React shadcn apps with one CLI command — shadcn · 2026-07-24
- FlickartHQ launches 3D Stage, an agentic 3D tool promising Blender-like results — SimplyAnnisa · 2026-07-24
- Tutorial shows how to deploy FLUX.2 on Amazon SageMaker AI with MCP support — huggingface · 2026-07-24
- Anthropic-linked researchers detail SharedRoot, a sandbox escape that can expose a host filesystem — EdenEmarco177 · 2026-07-24