> For the complete documentation index, see [llms.txt](https://docs.heeler.com/mrecEO40m5D6bt7Pq5pE/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.heeler.com/mrecEO40m5D6bt7Pq5pE/overview/what-is-heeler.md).

# What Heeler Is

What Heeler does, the four conditions it is built for, and how the Prevent, Fix and Operate layers act on its model of your software.

{% columns %}
{% column %}
Heeler is an application security platform for codebases where a large share of the code is written by AI coding agents. It connects read-only to your repositories, artifact registries and cloud accounts, builds a model of your software and the environments it runs in, and uses that model three ways: to check changes before they merge, to generate and validate fixes, and to drive each finding to a deployed remediation.

It is not a single-purpose scanner. Detection, prioritization, remediation and closure tracking all read from the same model, which is what lets a finding carry its service, exposure, owner and deadline from the moment it is raised.
{% endcolumn %}

{% column %}
{% hint style="info" %}
**Evaluating Heeler?** This page defines the product. To connect your first repository, go to [Get Started](/mrecEO40m5D6bt7Pq5pE/get-started.md).
{% endhint %}
{% endcolumn %}
{% endcolumns %}

## Conditions Heeler is built for

Four properties of an AI-assisted codebase shape how the product works:

<table><thead><tr><th width="260">Condition</th><th>Consequence for security</th></tr></thead><tbody><tr><td><strong>Code volume exceeds review capacity</strong></td><td>Agents generate more code than a team can read line by line, so checks have to run on every change without a reviewer in the path.</td></tr><tr><td><strong>Agents differ in security behavior</strong></td><td>Codex, Cursor, Claude Code, Copilot and in-house models have different defaults, so posture varies by which agent wrote the change.</td></tr><tr><td><strong>Skills and MCP servers are a dependency</strong></td><td>Agents execute external instruction files and MCP servers with the same trust as first-party code, which makes those files part of the supply chain.</td></tr><tr><td><strong>Existing risk classes still apply</strong></td><td>Dependency, code, secret and infrastructure risk are unchanged; what changes is the rate at which new instances appear.</td></tr></tbody></table>

## What the model is used for

Heeler builds one model of your software — repositories, dependencies, endpoints, services, deployments, infrastructure and agent files — and applies it at three points:

* [**Prevent**](/mrecEO40m5D6bt7Pq5pE/prevent.md) — your policy, approved versions, service tier and exposure data are available in the coding agent, in the CLI at the keyboard, and as a status check on every pull request.
* [**Fix**](/mrecEO40m5D6bt7Pq5pE/fix.md) — Heeler computes the dependency upgrade or code change for a finding, builds and tests it, and opens a pull request once your CI passes.
* [**Operate**](/mrecEO40m5D6bt7Pq5pE/operate.md) — findings are detected on every push, scored, put on an SLO, routed to the owning team by workflow, and closed only after the fix is observed in a running deployment.

```mermaid
%%{init: {'theme':'base','themeVariables':{'lineColor':'#9aa0b5','primaryColor':'#eef1f8','primaryTextColor':'#10163a','primaryBorderColor':'#c2c7de','fontSize':'14px'}}}%%
flowchart LR
    D[Detect<br/>every commit] --> P[Prioritize<br/>by exposure] --> R[Route<br/>to the owner] --> X[Fix<br/>validated PR] --> V["Verify<br/>deployed and closed"]:::anchor
    V -.->|continuous| D
    classDef anchor fill:#5A3FFF,color:#ffffff,stroke:#3a2ad0,stroke-width:1px;
```

## Related

* [The Context Model](/mrecEO40m5D6bt7Pq5pE/overview/the-context-model.md) — the six inputs the model is built from.
* [Prevent, Fix and Operate](/mrecEO40m5D6bt7Pq5pE/overview/three-layers-one-model.md) — what each layer does.
* [Get Started](/mrecEO40m5D6bt7Pq5pE/get-started.md) — connect your first repository.


---

# 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.heeler.com/mrecEO40m5D6bt7Pq5pE/overview/what-is-heeler.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.