Writing

Blog

Notes on building AI agents and the systems around them.

  1. 01

    Workflows vs. Agents: Choosing the Simplest Thing That Works

    Most LLM features don't need an agent. A practical way to decide between a single call, a workflow, and a fully autonomous agent.

  2. 02

    Designing Tools Your Agent Can Actually Use

    An agent is only as good as its tools. Naming, schemas, error messages, and output size matter more than the framework you pick.

  3. 03

    A Reference Architecture for Agents in Production

    The pieces around the model loop — state, sandboxing, observability, evals, and cost controls — that turn a demo into a dependable system.