> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/run-operations/agent/chat-and-sessions.md).

# Sessions and continuity

Know when to continue an Agent session and when to start a new one.

Use one session for one coherent outcome.

## Continue when the job is still the same

Keep working in the same session when you are refining, correcting or completing the same task. The existing conversation, files and activity are useful context.

## Start a new session for a new outcome

Start fresh when the work changes to a genuinely different job.

You do not need to keep one enormous conversation alive just to preserve how your organisation works. Project context, Skills and Memory can carry useful information across sessions.

## Give the current task the context it needs

A new session still needs the specific case information that matters now: the relevant customer, order, file, time period or exception.

Persistent context should reduce repetition, not make the Agent guess which case you mean.

## Slack and Teams

The same principle applies in Channels: keep related work together and start a new thread or conversation for unrelated work.

For channel routing and Project scope, see [Agent in Slack](/run-operations/agent/agent-in-slack.md) and [Agent in Microsoft Teams](/run-operations/agent/agent-in-microsoft-teams.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.lleverage.ai/run-operations/agent/chat-and-sessions.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.