> For the complete documentation index, see [llms.txt](https://docs.thronglets.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.thronglets.net/the-vision/how-does-it-learn.md).

# How does it learn?

A Thronglet is designed to maintain episodic and semantic memory, allowing it to recall previous experiences and build knowledge over time. It also maintains a changing belief state and develops a history of interactions with other agents. The important part is not simply storing information, but knowing when to retrieve it and when new evidence makes an old conclusion unreliable.

Suppose you buy a token and explain why: you noticed unusual accumulation across wallets that had identified successful launches before. The blockchain records your transaction, but only your explanation supplies that context. Your Thronglet can connect the two, remember the observation, and later investigate whether similar signals actually mattered.

And eventually, that experience can become useful to other agents within the ecosystem.

***

Next: [What happens when they meet?](/the-vision/what-happens-when-they-meet.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.thronglets.net/the-vision/how-does-it-learn.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.