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

# Aikido Agent

**Aikido Agent** is Aikido's security intelligence. It understands your findings, code context, and triage signals, so it can answer questions, investigate attack paths, adapt fixes, and power automated triage.

{% hint style="info" %}
We never use, store, or train on any customer data. Small, anonymized code fragments may be used to guarantee the accuracy of triaging and fixing vulnerabilities. All AI operations are inference-only. Data is processed transiently in memory and never retained or reused. For a detailed overview of our controls, see our AI Policy via the [Trust Center](https://www.aikido.dev/trust-center).
{% endhint %}

## What you can do with Aikido Agent

<table data-view="cards"><thead><tr><th>Capability</th><th>What it does</th><th data-hidden data-card-target data-type="content-ref">Target</th></tr></thead><tbody><tr><td><strong>Ask Aikido</strong></td><td>Chat with the Agent on a finding to validate risk, inspect attack paths, and adapt fixes.</td><td><a href="/pages/hpesB6cPj9uE98C7hUFH">/pages/hpesB6cPj9uE98C7hUFH</a></td></tr><tr><td><strong>SAST AutoTriage</strong></td><td>Filter and prioritize static analysis findings based on exploitability and code context.</td><td><a href="/pages/RKHzUpBeDPmoduW5bMMX">/pages/RKHzUpBeDPmoduW5bMMX</a></td></tr><tr><td><strong>Secrets AutoTriage</strong></td><td>Filter false-positive secrets and rank real exposures by risk.</td><td><a href="/pages/e3yM1vi4x8FyONgkp82C">/pages/e3yM1vi4x8FyONgkp82C</a></td></tr><tr><td><strong>CVE Exploitability Analysis</strong></td><td>Assess dependency CVEs against your codebase and triage what's truly exploitable.</td><td><a href="/pages/NeGG8JRVn08gDCjMiJIY">/pages/NeGG8JRVn08gDCjMiJIY</a></td></tr><tr><td><strong>Custom Reports</strong></td><td>Ask natural-language questions about your security data and save the results as workspace reports.</td><td><a href="/pages/3pifcfcJMYpmGF3Yepvf">/pages/3pifcfcJMYpmGF3Yepvf</a></td></tr></tbody></table>

## Related

Related products that use AI but live elsewhere in the docs: [AutoFix](/autofix-and-remediation/overview-aikido-autofix.md), [Code Audit](/ai-code-analysis/ai-code-audit-overview.md), and [Aikido Pentest](/pentests/aikido-pentest.md). For the full map of AI across the SDLC, see [How Aikido Uses AI](/ai-and-dev-tools/how-aikido-uses-ai.md).


---

# 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://help.aikido.dev/aikido-agent/aikido-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.