If you can describe what you want to the model, you can use zero-shot prompting for example
Classify the text into positive, neutral or negative:
Text: That shot selection was awesome.
Classification:
They introduce a concept called generative agents. They describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior.