> 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/build-and-improve/overview/custom-integrations.md).

# Custom integrations

Set up a custom integration with the Agent when the system you need is not available as a native Lleverage provider.

Industrial operations frequently depend on systems that are not covered by a standard SaaS connector: a customer-specific ERP endpoint, legacy API, internal service or vertical application. In Lleverage this is a **custom integration**.

### Two setup paths

The current Custom API entry point offers two routes:

![Custom integration setup can be started as a self-serve form or from the Agent.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2Fgit-blob-c499e140640c84bd16aba511ea40bbc2705f9e4d%2Fcustom-paths.png?alt=media)

* **Set it up yourself** — fill in the API details and credential setup.
* **Let the Agent connect it** — describe what needs to be connected in chat and let the Agent guide the setup.

The Agent-led path is often the most natural when you are already defining the work with the Agent. The self-serve path is useful when a builder already has the API details in hand.

### Secure credential handoff

The self-serve form captures the integration name, slug, API base URL, credential label, auth method and access scope. Supported auth methods currently include Bearer token, API key header, Basic auth, Query parameter, Custom header, OAuth2 client credentials and NTLM (Windows).

![The Custom API setup form immediately before the secure credential-entry handoff.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2Fgit-blob-66ef8c737c96d3af0a75e5fe506e7dd88ec3b011%2Fcustom-handoff.png?alt=media)

The next step opens a secure page for the credential value. **The credential is stored without needing to appear in Skills or chat.** Do not paste API keys or passwords into the Agent conversation, Skill instructions, files or Workflow payloads.

### Verify the capability

After setup, verify the intended environment, allowed read/write actions, access scope and the exact action the Agent needs from the correct Project. Treat endpoint, credential and action changes as production authority changes.


---

# 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/build-and-improve/overview/custom-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.