
Instruction systems capability ladder: harness leveling
submission for the Hermes Agent Challenge A few months ago I drew a maturity ladder for CLAUDE.md...

Author profile
Backend developer turned builder. 20 years in software, now building Reporails - instruction governance for coding agents. Writing about context engineering and patterns that make AI agents reliable.
Browse the latest writing surfaced through DevArt.

submission for the Hermes Agent Challenge A few months ago I drew a maturity ladder for CLAUDE.md...

Everybody has opinions about AGENTS.md/CLAUDE.md files. Best practices get shared. Templates get...

The AI agent ecosystem has built a serious industry around controlling outputs. Guardrails. Safety...

You thought of a pink elephant, didn't you? Same goes for LLMs too. "Do not use mocks in...

Two rules in the same file. Both say "don't mock." When working with external services, avoid using...

I watched an agent ignore a rule I wrote 2 hours earlier. Not a vague rule. A specific one. "run...

After a 2.5 hour session you accidentally close your coding agent terminal mid session. The output is...

I picture says a thousand words. I wanted to see my system. Not the code. I wanted to see the...

This is a submission for the GitHub Copilot CLI Challenge What I Built Reporails is a...

There's a Dutch scouting tradition called "dropping." Kids get driven to an unfamiliar forest at...

How do you learn new things as a developer? My take on it is to find yourself an actual...

The missing quality checker for AI instruction files. You asked for a small refactor. A small(!)...

The "build -> surprise -> restructure -> repeat" loop is amazing early on. However, after a...

The story of how a small prompt idea snowballed into a real agentic LangGraph runtime and I didn’t...