Knowledge
Concepts and Guides on engineering with and for AI agents, by category.
AI Engineering
Agent
A model harnessed with tools, a system prompt and a context window that takes turns with a user: the unit you actually talk to.
Model
The parameters: a stateless next-token predictor that can't do anything agentic until it is harnessed.
Token
The atomic unit a model reads and writes; context window size, cost and latency are all counted in tokens.
Context Engineering
Clearing
Ending the current session and starting a fresh one with an empty context window.
Compaction
A handoff done in-memory: the session's history is summarised and the summary seeds a fresh session.
Context
The task-relevant information the agent has access to right now, as distinct from the context window and the session.
Context window
Everything the model sees on each model provider request: finite, model-specific, and the only surface through which it perceives anything.
Session
One bounded run of interaction with an agent; the session is what fills the context window.
Smart zone
The early, sharp part of a session, before growing context drifts the agent into a sloppier "dumb zone".