VoicesWillison Red Green TDD for AI Agentssimonwillison.net·high signalAppend Use red/green TDD to agent prompts. Three words, immediate quality improvement. Published as structured guide at agentic-engineering-patterns.SourceSource pagesimonwillison.net↳ Follow the threadStack layerArmin Ronacher's 'The Tower Keeps Rising': AI Agents Erode the Coordination Friction That Kept Teams in SyncSimon Willison / Armin RonacherStack layerTip: Newer Anthropic Models Do Worse With Custom Edit Tools — Prefer the Native Editor FormatSimon WillisonStack layerDOOMQL: A Playable Doom-Like in 2,000+ Lines of Pure SQL, Built With GPT-5.6 Sol — Simon Willison Amplifies and Ships His Own Sol Codesimonwillison.netPolicy dependencySimon Willison Finds a Cache-Friendly uvx Recipe for GitHub Actions: Pin UV_EXCLUDE_NEWER Into the Cache KeySimon WillisonStack layerArmin Ronacher on the real shared language of a software projectSimon Willison's BlogPolicy dependency / Stack layerCynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write PermissionsIT Security NewsPolicy dependency / Stack layerGoogle Hit With Another AI-Training Copyright Suit From Major PublishersTechCrunchSame source domain / Semantic neighborTip: Give Agents Judgment, Not Scripts — Delegate the Small Stuff to Lower-Tier SubagentsSimon Willison