A model in a loop with tools is a different kind of software.
L7 · Agents
An agent is a loop: think, call a tool, read the result, repeat until done. That small change turns a text generator into something that can act, and it brings every problem that comes with acting. This chapter covers tool design, memory, permissions and cost control, because those are what decide whether an agent is useful or a liability. You will also learn to evaluate agents on tasks rather than on transcripts that read well.
- The Loop
- Tools Are Functions With Descriptions
- Tool Output Is Data, Not Orders
- Planning
- Memory Between Steps
- More Than One Agent
- Tool Protocols
- Guardrails and Permission Models
- Loops, Hallucinated Tools and Stalls
- Evaluating Agents
- Keeping the Bill Sane
- What They Can Do Today