Autonomous Agents: Memory and Tools

Part of the Prompt Engineering course

In lesson 5 you gave a model tools through function calling, and in lesson 6 you gave it long-term memory through retrieval. This lesson puts those two pieces inside a loop so the model can act, look at the result, and decide what to do next, over and over, until a goal is met. That loop is what turns a model that answers once into an agent that works toward something.

Everything so far has been a single exchange. You send a prompt, the model sends back text, and you are done. That is a powerful shape, but it has a ceiling: the model cannot check its own work, gather a missing fact, or take a second step based on what the first step produced. ...