I Built an Anti-Sycophancy System for My AI Coding Agent
When your AI assistant agrees with everything you say, including the things you get wrong, you have a compliance problem. Here is how I fixed it with hooks, rules, and adversarial agents.
Writing
Thoughts on UX design, product development, design systems, and building things that work.
When your AI assistant agrees with everything you say, including the things you get wrong, you have a compliance problem. Here is how I fixed it with hooks, rules, and adversarial agents.
When your interface lives on two devices, the user can only look at one. Sound, haptics, and invisible latency absorption become your real design tools.
I have ADHD. Most learning tools ignore that. So I built one that doesn't.
Node graphs demo beautifully with 5 nodes. At 15 they become unreadable. The problem is topology, not tooling.
The right prototyping tool depends on the question you're trying to answer, not the phase you're in. Sometimes paper beats Figma and code beats both.
Most workshops produce sticky notes and good vibes. A few produce one insight that reframes everything. The difference is the setup, not the activities.
Want to know when new posts go live?
Follow on LinkedIn