The Centaur's Toolkit

This is Part 3 of “The Centaur’s Toolkit” series. We’ve covered AI pair programming fundamentals and building AI-assisted security tools. Now we tackle the hardest skill: knowing when to trust what AI tells you. Last week, I asked an AI to help me understand a library I’d never used. It gave me a confident, detailed explanation of the validateSchema() method, complete with parameter descriptions and example usage. The method doesn’t exist. The AI invented it. The explanation was coherent, the examples looked plausible, and if I hadn’t tried to actually use the code, I might have wasted hours debugging a function call to something that was never real. ...

This is Part 2 of “The Centaur’s Toolkit” series. In Part 1, we covered the four collaboration modes for AI pair programming. Now we apply that framework to higher-stakes territory: security. You’ve embraced AI pair programming. You’re using Strategist mode for architecture, Editor mode for refinement, and you feel like a genuine Centaur. Then your manager asks you to build a security tool. Suddenly, the stakes feel different. In regular coding, an AI-suggested bug might waste a few hours of debugging. In security, an AI-suggested bug might become a vulnerability that sits in production for months. The cost of being wrong isn’t just time. It’s trust, data, and potentially your users’ safety. ...

This is Part 1 of “The Centaur’s Toolkit” series, where we explore practical strategies for human-AI collaboration in technical work. You’ve been using GitHub Copilot for six months. Or maybe it’s Claude, ChatGPT, or Cursor. The tab key has become your best friend. Boilerplate code that used to take twenty minutes now takes two. You feel faster. More productive. Like a coding superhero. But lately, something feels off. You catch yourself accepting suggestions without really reading them. You accept a function completion and realize you’re not entirely sure what it does. Yesterday, you spent an hour debugging code that the AI wrote, code you wouldn’t have written that way yourself. ...