> 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/agent-context/integrations.md).

# Connected systems

Understand how the Agent uses authorised Connections to work with external business systems.

The Agent can work with systems such as ERP, CRM, email, spreadsheets, document stores and collaboration tools when the required Connection is available to the current run.

A Connection gives Lleverage authorised access to the external system. The operating method still comes from the task, Skill and Project context.

**The Connection provides authority. The Skill provides the method.**

## What this can enable

Depending on the provider and your access, the Agent may be able to:

* look up live business data;
* retrieve messages or files;
* create or update records;
* perform other enabled actions.

Connecting a system does not by itself teach the Agent your business rules.

## Project and channel context matter

A web Agent session has an explicit Project.

Slack and Teams can also run without one fixed Project. In that case, eligible connected capabilities are resolved only from Projects the acting user is authorised to access.

If a capability works in the web Project but not in a Channel, first check the conversation's Project routing and your access. Pin the conversation when the task should use one Project's exact systems and context.

## If the system is not connected

For supported providers, the Agent can help initiate setup when the work needs a system that is not yet authorised.

You complete the provider login or secure credential step. Do not paste passwords, API keys or other secrets into the conversation.

## What you can inspect

When the Agent uses a connected-system tool, the session exposes activity around the work. Builders can use Monitoring for deeper diagnosis.

The permissions of the external account remain real even if Lleverage exposes only selected actions. Use the right external permissions and approval boundaries for consequential writes.

For setup and provider-specific controls, see [Connections](/administer-and-govern/control/connections.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/agent-context/integrations.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.