Weekly letter on AI agents and automation

Notes from building real automations.

Short letters on how AI agents actually work when money is on the line.

What you'll find inside

Short letters on how AI agents actually work when money's on the line.

i.
Real builds, broken down
Walkthroughs of systems I've shipped for clients. What worked, what broke, and the part I redesigned three times before it held.
ii.
Patterns for agentic systems
How to structure prompts, route between models, handle failure gracefully, and keep agents from spiraling into expensive nonsense.
iii.
Honest notes on the tools
Make, n8n, GoHighLevel, Claude, OpenAI. When to reach for which. The tradeoffs nobody mentions in the tutorials.
iv.
Things I'm figuring out
Half-formed ideas. Things I'm stuck on. This letter doubles as my thinking-out-loud space, and you get a front-row seat.