Making models useful

Agents, tool calls and the plumbing that makes a model genuinely useful inside a real system.

2 notes

12 Sep 2026, 7 min read
12 Sep 2026, 7 min read
What I got wrong about tool calling — and why designing tools like an API fixed most of it
I assumed the model would use the tools sensibly. It did not. What changed once I started designing tools the way I design an API: narrower inputs, typed arguments, and error messages written for the model rather than for me.
- Agents
- LLMs
- AI architecture
- +2 more
09 Jul 2026, 5 min read
09 Jul 2026, 5 min read
Why I am learning AI agents
Less about the hype, more about a specific kind of repetitive work I would like a program to take off my hands.
- Agents

Have a system worth arguing about?

I am always up for a conversation about architecture, trade-offs, or a bug that refuses to die.