/01 Journal
Practical writing on
AI agents in production.
No hype. No "the future of AI" think-pieces. Just what we've learned shipping agents to real teams — evals, architecture decisions, failure modes, and what actually moves the needle.
// Coming soon
First issues in the works.
We're writing about the things that actually matter when you ship agents to production — eval design, retrieval quality, monitoring, and why most AI demos don't survive contact with real users.
Get notified — book an intro call →Topics we'll cover
Eval-driven prompt engineering
RAG retrieval quality
Agent observability
When not to use AI
Multi-agent architectures
Production incident post-mortems