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

# havl Documentation

**The Human Layer for AI & Robotics.**

havl connects AI systems, autonomous agents, and robotics with a distributed network of human verifiers. Applications can escalate uncertain or high-impact decisions to people, collect structured judgments, and continue automatically once the required confidence or consensus is reached.

## What you can do with havl

* Verify AI-generated outputs before they reach users or downstream systems.
* Add human approval gates to autonomous agents.
* Escalate ambiguous or high-impact actions for independent review.
* Route robotics edge cases to human operators or experts.
* Use verifier levels, reputation, Certified Experts, and consensus to match review quality to task risk.

## Explore the documentation

Start with **Getting Started** for the core concepts, **Products** for the three havl product lines, or **Integrate havl** for the API and webhook model.

{% hint style="info" %}
havl is under active development. Technical interfaces and network mechanics described in these docs may evolve before production launch.
{% endhint %}


---

# 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.havl.io/havl-documentation.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.