> For the complete documentation index, see [llms.txt](https://docs.ilert.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ilert.com/ai-and-agents/ai-features/global-search-enhanced-by-ilert-ai.md).
# AI global search
Access all resources in your ilert account easily. Search alerts, incidents, users, and alert sources.
## Searching for resources
ilert global search is a superfast way to access any resource in your ilert account. No matter if master data like alert sources or dynamic data such as alerts or incidents.
Locate it at the top of your navigation bar in any view or press `CTRL/CMD + K` to open the search bar. Enter your desired search term and wait a moment for your results to be gathered.
The result window gives you a quick glance over all resource types in your account that match the search term. ilert uses a hybrid search approach that mixes full-text search and vector similarity with reranking to provide you with the best results to your search, even if your search term is not exactly matching.
## Drilling down deeper
You may drill down into more results for a specific category, this will widen the vectorized search part as well, trying to resolve even more results. Just **click on a category header** of your search results.
This will open the category specific results:
{% hint style="info" %}
Note that by hovering a result you can see the full text of the item
{% endhint %}
## Mouseless usage
You may use the search without interacting with your mouse.
1. Press `CTRL / CMD + K` to open the search bar
2. Enter your search term
3. Press Enter to open the detail view of the first top result
---
# 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.ilert.com/ai-and-agents/ai-features/global-search-enhanced-by-ilert-ai.md?ask=&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.
