AI Engineering
Small Bugs Should Not Wait for a Free Afternoon
How we connected production logs to a coding agent that reproduces a bug, fixes it and opens a pull request, while engineers keep the merge.
Archive
2026
7 posts from 2026
AI Engineering
Omni Loop: Agents Ship, You Steer
Why I built a delivery framework for coding agents, how the loop runs from idea to retro, and the three rules that keep people in charge.
AI Engineering
Before Building Another MCP, Make Your Codebase Agent-Ready
Eight dimensions that decide whether a coding agent becomes effective in your codebase, and why the limiting factor is almost never the model.
AI Engineering
AI Should Generate Manifests, Not Code
Generated code is unpredictable, hard to maintain, and expensive to validate. There is a better way: let AI generate structured declarations, and let a deterministic runtime handle the rest.
AI Strategy
You Might Not Need AI
A practical essay on when AI creates value, when it creates unnecessary complexity, and why deterministic problems often deserve deterministic solutions.
Data Strategy
Five Dimensions of Data Readiness — and Why Each One Matters
Before any AI project starts, five questions about your data need honest answers. Access, quality, ownership, compliance, and freshness. Here is what each one reveals — and what happens when you skip it.
AI Strategy
Before You Build AI, Ask These Five Questions
Most AI projects don't fail because of the technology. They fail because no one asked the right questions before starting. Here is how I assess readiness — and why each dimension matters.