> For the complete documentation index, see [llms.txt](https://docs.datalinker.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datalinker.ai/data-linker/threads-within-chat-categories/how-should-i-utilise-the-thread-function.md).
# How should I utilise the thread function?
1. Threads can be used for a variety of purposes such as isolating topics within a chat category, bypassing the poisoned pond effect, which happens when random topics and logic is discussed (at large) within a single thread, confusing the agenda of the topic at hand.
2. Threads can be shared by first select the thread and turning on collaboration
3. Threads will automatically be created when the user starts a conversation within the selected chat category.
4. Existing Threads can be located by navigating to the top of the page of the selected chat category and then by clicking the threads dropdown button (Located next to the blue + button). Doing so will provide the user with a list of all their existing threads.
5. Clicking on an Existing Thread will load up that thread's history and the user can take further action by discussing the topic further in isolation or enable collaboration allowing other users to interact live in collaboration.
6. To manually create a new thread click the blue + button.
---
# 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 dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.datalinker.ai/data-linker/threads-within-chat-categories/how-should-i-utilise-the-thread-function.md?ask=
```
The question should be specific, self-contained, and written in natural language.
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.