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.
Writing
Notes on building AI agents and the systems around them.
Most LLM features don't need an agent. A practical way to decide between a single call, a workflow, and a fully autonomous agent.
An agent is only as good as its tools. Naming, schemas, error messages, and output size matter more than the framework you pick.
The pieces around the model loop — state, sandboxing, observability, evals, and cost controls — that turn a demo into a dependable system.
Newsletter
Practical notes on AI agents and system architecture. No spam, unsubscribe anytime.