CH 01 · Anatomy of an AI Agent · 01/12
Read as one pageAnatomy of an AI Agent
An AI agent has six parts: the model, the loop, tools, context, memory, and the surrounding system. How each one behaves and how they interact in one turn.
12 slides · 14 min read
In this chapter
- 01The spectrum: prompt → chatbot → agent
- 02The six parts
- 03Real code: Hermes Agent assembles all six parts in one function
- 04Real code: Hermes keeps long-term memory in two small files
- 05How the parts interact in one turn
- 06Real code: OpenClaw checks the caller before any agent work
- 07Real code: one smolagents step, from memory to model and back
- 08A crucial reframing: the model is the easy part
- 09Real code: in pi, the model call is one line of a long file
- 10Two stances toward the model
- 11Read the source yourself
Before you can design an agent, you need a clear mental model of its parts. This chapter lays out that anatomy and the vocabulary the rest of the folder uses. Every term here recurs throughout, so it's worth getting precise.
Finished this idea?
Your learning progress stays in this browser.