> 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

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/sIHaMo3AX1Cs4cfeaxpc" %}

{% 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.vectra.ai/operations/analyst-guidance/understanding-vectra-ai-detections.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.