CPTO with 20 years building products at the intersection of engineering, product, and design. I write code, shape product strategy, and design user experiences. Currently leading development of AI-driven GRC platform at Complyance, where we're building intelligent systems that understand complex regulatory workflows.
I applied the MAST failure taxonomy to 639,000 execution steps from AI agents running in production for five months. My first headline finding turned out to be an infrastructure bug masquerading as agent behavior. This post is about what agents actually fail at in production, and the discipline it takes to not fool yourself with production data.
I just published LHC v0.2, an open benchmark for long-horizon coherence in 8B-class agent models, plus a deterministic parser baseline that puts a useful floor on what fine-tuning is worth for structured-state tasks. This post explains what they're for, how to use them, and the methodology arc that produced them across five rounds of external review.
The self-hosted AI agent movement is real and important. But we are confusing a bootstrap phase with a destination architecture. The long-term future of agents will be defined by platforms that make them reliable, governable, and operationally boring.
When execution becomes abundant through AI agents, judgment becomes the bottleneck. The traditional separation between technical and product leadership breaks down, creating space for the CPTO role.
OWASP just published their first Top 10 for Agentic Applications. Here's what every agent builder needs to know about the new attack surfaces, why traditional security fails, and how the orchestration layer becomes the new security boundary.
OpenClaw went from viral sensation to security nightmare. Today, OpenAI launched Frontier. Two sides of the same story: autonomous agents are going mainstream, and the infrastructure isn't ready.
Demos run for minutes. Production runs for hours. Here's what breaks, and the durability patterns that actually work when your agent needs to make 200+ tool calls without losing its mind.
A response to the viral "spec as code" thesis. We don't stop programming—we change what programming means. And that change requires more engineering fundamentals, not fewer.
Intelligence without infrastructure is just a demo. Here's why the Agent Harness thesis matters and what I've learned building autonomous agents that actually work.
A practitioner's look back at what happened in AI agents in 2025—from DeepSeek shaking the markets to GPT-5, Gemini 3, and the rise of agentic AI.
Why memory architecture is the hidden bottleneck in AI agent systems, and the patterns that actually work in production.
Real data showing 1082% productivity gains with AI coding tools. GitHub metrics, workflow diagrams, and evidence-based response to AI coding skeptics with 146,000 lines shipped in 4 months.
