AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
chunking — Splitting documents into passages small enough to embed and retrieve individually — the step that quietly determines whether retrieval works at all.
Why it matters
If you are building agents that need to work for hours or days, the hard part is not the model — it is chunkingSplitting documents into passages small enough to embed and retrieve individually — the step that quietly determines whether retrieval works at all.Full definition → work so each unit fits one context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → and every unit is independently verifiable. This lays out Factory.ai's answer: strict separation of concerns plus test-driven verification applied at both the mission and task level.
