Writing
Thoughts on building software that lasts, AI that actually helps, and lessons from 30 years of production code.
2026
Why Half of All AI Projects Fail
Gartner found 50% of GenAI projects were abandoned after proof of concept. HBR reports only 1 in 50 deliver transformation. The failures aren't technical—they're organizational. Here's what the survivors do differently.
OpenClaw Isn't Just Another AI Tool. It's the Beginning of the AI Workforce.
An open-source project just crossed 145,000 GitHub stars in weeks. Developers are deploying autonomous agents that execute tasks while they sleep. This is the moment AI stopped being a tool you use and became a worker you deploy.
The 40+ Year-Old Rule AI-Generated Code Is About to Crash Into
A four-decade-old lesson explains why AI-generated code gets expensive fast: the later you discover the mistake, the more you pay to unwind it.
2025
Your AI Pilot Worked Because It Wasn't Production: Here's What You Have to Change
MIT says 95% of enterprise AI pilots fail to deliver ROI. The problem isn't the model—it's that production systems are architecturally different from pilots. Here's what 20 years of running production healthcare systems taught me about that gap.
Context Stacks: Why Real AI Engineers Don't Care About Prompts
The people building serious AI products aren't obsessing over magic words. They're designing context stacks—and that changes everything about how you should think about prompts.