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

# Understanding Vectra AI detections

Understand Vectra AI detection models and the behaviors they identify.

This KB article serves as the replacement for all other KB articles that contained various prior versions of this document. There is also a JSON version which can be used as metadata to enrich Vectra Detections in third-party tools like Tines that are ingesting Vectra detections via API or Syslog.

For scoring guidance:

* RUX users: individual detections are no longer scored; instead, Vectra prioritizes host and account entities for analysts with [AI-driven Prioritization](/reference/ai-driven-priortization-faq.md)
* QUX users: individual one-pager detection explanations with Threat and Certainty ranges are available in each individual detection in the UI

{% file src="/files/PBZ0huOHjGJuJdrYE4V8" %}

{% file src="/files/OFhEUW164GgnE6AeiPfp" %}

{% hint style="warning" %}
**Please Note:**

We’ve updated the JSON file that accompanies the formal .pdf file.

As part of this update, the content of the `info` section has changed. If you rely on automated parsing of this JSON, you should review and validate your parsing logic to ensure everything continues to function as expected.

We recommend testing your integrations against the updated structure to avoid any potential disruptions.
{% endhint %}

{% hint style="info" %}
If you are uncertain of which UX you are using, please see [Vectra Analyst User Experiences (Respond vs Quadrant)](/deployment/getting-started/analyst-ux-options-rux-vs-qux.md).
{% 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.vectra.ai/operations/analyst-guidance/understanding-vectra-ai-detections.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.