> 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/products.md).

# Products

havl provides one human verification network across three product families.

Each product brings human judgment into a different stage of autonomous systems — from AI-generated outputs to agent actions and physical-world decisions.

### Three Products. One Human Layer.

#### havl verify

**Human verification for AI outputs.**

Validate classifications, generated answers, extracted information, visual interpretations and other model outputs when additional confidence is required.

**Verify what AI produces.**

#### havl guard

**Human oversight for autonomous agents.**

Introduce human checkpoints when agents reach sensitive, high-impact or predefined boundaries — without requiring approval for every action.

**Oversee what agents do.**

#### havl motion

**Human intervention for autonomous machines.**

Escalate uncertain perception, unusual situations and physical-world edge cases to humans when autonomous systems need additional judgment.

**Resolve what machines can't.**

### At a Glance

| Product         | Primary use                 | Typical trigger                                                |
| --------------- | --------------------------- | -------------------------------------------------------------- |
| **havl verify** | Validate AI outputs         | Low confidence, sensitive output, quality check                |
| **havl guard**  | Oversee autonomous agents   | High-impact action, policy boundary, approval request          |
| **havl motion** | Resolve robotics edge cases | Uncertain perception, blocked action, physical-world exception |

All three products use the same underlying havl network and verification model.


---

# 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/products.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.