# Implementing Working Memory

In this step, we'll explore working memory, which allows your agent to maintain persistent information about users across interactions within a thread.

## What is Working Memory?

Working memory is like your agent's active thoughts or scratchpad – it's the key information they keep available about the user or task. It's similar to how a person would naturally remember someone's name, preferences, or important details during a conversation.

Unlike conversation history and semantic recall, which focus on remembering past messages, working memory is designed to store structured information that's continuously relevant, such as:

- User profile information (name, location, preferences)
- Task-specific details (project goals, deadlines)
- Session state (current topic, open questions)

Working memory provides a way for your agent to maintain a persistent understanding of the user and the context of the conversation, even as the specific messages in the conversation history change. This allows your agent to provide more personalized and contextual responses over time.