2.1 · Lesson

The Stateless Agent Problem

Go to glossary for large language model (opens in a new tab)A model trained on text to predict the next token, and so to generate language. have no memory between requests. Every call to the model starts from a blank slate — the model only knows what you include in the current prompt. This is fine for single-turn Q&A, but it fails immediately for real agent tasks.

In this lesson, you will learn what goes wrong without conversation memory and what short-term memory needs to provide.