AI in production
Architecture, evaluation, and operational decisions for AI-enabled software, illustrated through worked examples and technical investigations.
6 published articles
Articles
September 25, 2026
“Which Customers Are Affected?” Is an Architecture Question
A service-retirement example shows how to turn an ambiguous request into a bounded domain model, source responsibilities, and an architecture decision.
September 18, 2026
Stop Teaching Every Agent Your Business from Scratch
When several AI applications reconstruct the same business relationships, the architectural question is what the organization should maintain once and share.
August 28, 2026
Design Systems, Storybook and AI-Assisted Development
Follow a supplier contact form from design decisions in Figma to shared tokens, components and Storybook examples. Then give an AI assistant access to the same APIs and patterns, so it can build on the system the team maintains.
August 18, 2026
AGENTS.md: Writing Useful Instructions for Coding Agents
Build an AGENTS.md around a real repository task. Write concrete instructions, choose their scope, check how Codex or Claude Code loads them, and evaluate the result before adding more guidance.
August 16, 2026
The Agent Works Like a New Hire
A capable assistant can investigate broadly while its tools limit what it may commit. An invoice and a coding workflow show where reusable tools, automatic approvals and human judgment fit, and why approval fatigue deserves more than another button.
August 11, 2026
AI Agent Architecture: A Replenishment System Example
Follow a nightly replenishment agent from inventory analysis to buyer approval. Work through its permissions, interface, MCP and A2A integrations, data destinations, and a printable architecture worksheet.