> 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/investigate-quick-start-guide-prior-to-sql-search.md).

# Investigate Quick Start Guide (prior to SQL search)

For additional information about Vectra's Investigation features (Advanced Investigation and Instant Investigation), please see the [Vectra AI Platform Investigation FAQ](/operations/investigate/vectra-ai-platform-investigate-faq.md) .

**Contains**

* What is Vectra Investigate?
* Before you begin
* How to create and run a query
* How to add or remove filters
* How to modify the query's search period
* How to add/remove and re-order columns in the results
* How to run a query from Instant Investigation
* Query Examples
  * Investigating an Azure AD attack with Powershell
  * Investigating a Microsoft 365 attack with Power Automate
  * All activity around a specific AWS EC2 instance
  * AWS activity performed with an assumed role
  * AWS activity performed with an assumed role on a different region
* Troubleshooting
* "Search could not be completed" or "Search timed out"
* "Search could not be completed" (with error id)
* "Something went wrong"
* Related articles

**Attachments**

{% file src="/files/Tws5mED7oV8EYKmDm3Sq" %}


---

# 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/investigate-quick-start-guide-prior-to-sql-search.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.