Posts
All articles on AI-native work patterns, agent infrastructure, and what actually works when running agents as real tools.
-
From Failure Mode to Skill Chain
When an agent leaked a Slack channel ID by bypassing the scrub-and-publish skill, the fix wasn't a memory — it was wiring three skills together so the chain self-enforces.
-
Your Agent's Behavior Is Code — Start Versioning It
AI agent behavior committed to a repo travels with the codebase — reviewable, diffable, available to every contributor on first checkout. Treating skills as code artifacts converts ad hoc agent use into an institutionalized team process.
-
The Skill Is the Teacher
We've been naming AI skills like tools. That's the wrong frame — and it's quietly limiting how much value teams get from them.
-
/clear is not /exit — the session habit every Claude Code power user gets wrong
How a single misunderstood command caused a system crash — and the session hygiene pattern that fixes it.
-
The filesystem is your agent's routing layer
Stop organizing your files for humans. Here's what changes when you organize them for agents instead.
-
The Right Model for the Right Job
Model selection is an architectural decision — defaulting to the strongest model for every step in a pipeline is a pattern worth breaking.
-
Claude Code Has Native OpenTelemetry. Almost Nobody Knows.
Claude Code ships with a full OTel SDK that's off by default — here's how to turn it on, run a local Prometheus/Grafana stack, and actually see what your sessions are doing.
-
How Many Claude Code Sessions Can — and Should — You Run Simultaneously?
The question splits into two: can is a systems problem, should is a human one — and most people crash on the wrong side.