• Anthropic's definition of safety is too narrow. Anthropic treats safety as a model behavior problem. Claude Code's recent month shows it's also reliability, pricing, and communication. They're where trust actually gets spent.
• Resisting AI. The skeptics say AI is another Kubernetes — a misapplied tech hype cycle. I think it looks more like the Internet, and probably much more.
• Make it impossible, or Make it safe. My dad's safety philosophy turns out to be a great framework for agentic coding: don't bubble-wrap the world, engineer one where you can take risks.
• Early observations from Interviews with Engineering Teams Adopting AI. The teams succeeding with AI aren't the ones with the best tooling. They're the ones that changed how they work.
• The first PRs shipped by Customer Success. Last week our customer success team shipped their first two pull requests. It changed how we ship and how we communicate.
• Battleship Prompts. Same task, three different prompts. See which one gets closest. It's surprisingly effective and makes you a better prompter.
• The Claude Dichotomy. AI is creating a genuine dichotomy: teams drowning in AI-supercharged chaos, others are thriving. The difference is in the approach to transformation.
• Tool Augmented Prompting. Your linter, compiler, and test runner already talk to the AI. Make them say something useful.
• Do as I say not as I TODO. Your AI assistant holds a mirror up to your codebase. 5 ways to make sure it reflects the good parts.
• No agents, no plan, ship it. Why I prefer single-prompt one-shotting with AI coding tools over multi-step agents, swarms, and planning modes.
• Faster horses and AI Productivity. Not all AI productivity gains are real. A framework for telling the faster horses from the genuine improvements.
• The 'Comment-Only' Prompt. A new prompt I've found useful: Don't make any changes, just put a comment where you intend to make changes.
• What does it take to build towards 100 PRs/day per engineer? My day, my tooling, and the system changes that make high-volume AI-assisted shipping possible.
• Views of the Same Thing. Specs, code, tests and docs are projections of one intent. Humans keep several to triangulate. The cost is drift. An agent that reads the code directly may need fewer (or one?).
• Rent Versus Buy. A subscription makes idle capacity feel like loss. API pricing makes every call feel like spend. Same tokens, opposite behavior.
• Twenty Twenty Sprints. How I structure my day in 2x20-minute sprints an hour -- a pomodoro shape that fell out of AI coding.
• Straight to Claude. The moment a task or chore enters my head, it goes into Claude Code.
• Context Windows for People. You can't A/B test a performance review. When the feedback loop is too slow to iterate, you have to start with the right inputs -- and then try to break them before reality does.
• Let It Rate. With messy people data and long feedback loops, output schema isn't just an interface concern -- it's a useful steering mechanism.
• Being A Better Manager in the AI Era. AI is collapsing the value of coordination. If that was your primary value as a manager, you have a problem.
• We're not vibe engineering. Vibe coding is the headline. Engineering a new SDLC is the actual work.
• Clear Your AI Mind. Your context window is not a diary, don't forget to /clear.
• Spin the Bottle Neck. The bottleneck in software has moved. Teams are still optimising for the old (wrong) one.
• Skills I'm ceding to AI. My shortlist of coding skills I'm genuinely comfortable handing to AI.
• Don't Believe the Hype. AI vibe coding tools aren't truly there yet. But early adopters can see they will be. Those aren't the same thing.
• Infinite Monkeys. AI coding tools need a high degree of parallelism to work. Without it, you're just watching a monkey type.
• Know Your Models. Software engineers routinely juggle multiple AI models. Other disciplines will be encountering this soon.
• Sharpening the Axe (Branch). Using an Axe branch when iterating on your AI coding workflow.
• A Daily AI Chat. I'm using a single long-running AI chat each day to prioritize in the morning and summarize at the end.
• Skilled Humans in the Loop. Human-in-the-loop only works if the human has (and retains) the skills to actually be in the loop.
• My Current AI Coding Workflow. A snapshot of how I'm working with AI coding tools right now (Feb 2026).
• Your Brain on GPS. What happens to our navigation skills when we rely on GPS? And what might happen to our coding skills with AI?
• The Mythical Machine-Month. We're moving into an era where a team of 5 engineers can outperform a team of 50.
• The pace of AI tools. The rate that AI coding tools are adding workflow features is wild.