Notes from production.
Written for operations and engineering leaders putting AI into production: practical notes on building agents and automations that hold up, the integration work that decides whether they ship, and the trade-offs we hit running them day to day. No hype, no listicles.
Insights 
Most AI Agents Aren't Production Ready
52% of enterprises say they have AI agents deployed. Only 5% worry about tool-calling accuracy. The gap between 'deployed' and 'reliable' is where the real work begins.
AI Strategy 
The Shift to Agentic: Why Basic Chatbots Are Dead
Reading is passive. Real value comes from execution. Modern agents treat the LLM as a routing engine, validating inputs, calling tools through MCP, and gating destructive actions behind a human, not as a chat surface bolted onto a product.
Insights 
Why 'Glue Code' Is the Most Important Skill in Modern Engineering
Stripe, Salesforce, and your own DB each think a 'Customer' is something different. The real engineering work isn't writing the pieces, it's making ten systems that disagree about reality stay in sync without ever dropping a task or duplicating an order.