> For the complete documentation index, see [llms.txt](https://docs.enate.net/enate-help/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.enate.net/enate-help/enateai/enateai/supervision-agent.md).

# Supervision Agent

### What is Supervision Agent?

Supervision Agent brings your AI agents into Enate's orchestration platform, so every agent outcome is reviewed by a human before action is taken. Your agents and your people work together in a single, connected workflow, with humans always in the loop.

### How does it work?

Integrate any agent into Enate via API calls, with no vendor lock-in. Enate captures each agent's output and presents it to a human reviewer to assess and determine the next best action, keeping every agentic workflow supervised throughout.

### What are the benefits?

* Embed your own or third-party agents into existing workflows.
* Maintain human oversight at every decision point, so no agent acts alone.
* Run multi-agent workflows within a single platform.
* Swap or test agents at any time without rebuilding your processes.

### Worked example: Client Onboarding

Supervision Agent oversees a network of specialized agents in a Client Onboarding process. It triggers the other agents, collates their output, provides human-in-the-loop review, and logs every agent interaction.

| Agent in the network       | Role                                                                                               |
| -------------------------- | -------------------------------------------------------------------------------------------------- |
| **Internal Context agent** | Retrieves client and account data from your entity management system.                              |
| **External Context agent** | Gathers entity intelligence from trusted sources such as Bloomberg Finance.                        |
| **Transactability agent**  | Cross-references your SOPs with retrieved data to identify gaps and confirm readiness.             |
| **Risk Assessment agent**  | Analyzes collected data to assign a risk score and recommend next steps.                           |
| **Outreach agent**         | Compiles missing information and contacts the relevant party to request it.                        |
| **Execution agent**        | Acts on the outputs of all agents, approving, executing or escalating, with full context attached. |

At the center, a **Human Review** step checks the Supervision Agent's collated output before any action is taken.


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.enate.net/enate-help/enateai/enateai/supervision-agent.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.