8 min read
What 300 Incidents Taught Us About Agentic Context
We fed 300 real incidents to an AI pipeline. The context patterns that emerged changed how we think about agent knowledge.
WRITINGS/6 pieces
- 1 min readMedium
Contained Chaos: A Prototyping Operating Model for the AI Era →
Your enterprise has a prototyping problem. Not too little. Too much. Here's how to channel it without killing innovation or losing control.
- 1 min readDev.to
Architecture Catalog: Generate Diagrams from Markdown in Git →
An open-source tool that generates interactive context maps, event flows, and dependency graphs from plain Markdown + YAML in Git.
- 1 min readMedium
Forensic DDD: Reverse-Engineering Domains from Legacy Systems That Won't Talk →
Eight techniques for extracting domain boundaries from production systems when documentation is missing and original builders are gone.
- 1 min readMedium
Beyond the Architecture Police: 80% Inspiration, 20% Automation →
Why governance alone kills architecture adoption — and what actually works when teams have a hundred other priorities.
- 1 min readMedium
Demand-Driven Context: Teaching AI Agents to Remember What Matters →
A framework for enterprise AI agents that stops trying to document everything and starts letting problems drive what gets curated.