> 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/introduction.md).

# Overview

The ilert AI ecosystem combines **assistive AI features** that enhance user workflows with **autonomous agents** that can reason, investigate, and act on incidents using connected data sources through **MCP servers**.

ilert AI is built around two complementary layers:

1. **AI Features:** Assistive capabilities embedded directly into existing ilert workflows (e.g. alert grouping, post-mortem generation, incident message generation).
2. **Agents:** Autonomous, reasoning-driven agents that analyze signals, identify causes, and trigger actions to resolve or communicate incidents.

Together, they enable **AI-first incident management**, from detection to resolution, while keeping engineers fully in control.

### Model endpoints & data residency

ilert AI operates on region-specific model endpoints. Which models serve your organization depends on your region:

| Region                              | Model Hosting               | Provider                                                                                          |
| ----------------------------------- | --------------------------- | ------------------------------------------------------------------------------------------------- |
| **EU customers**                    | Models hosted **in the EU** | Anthropic models via **AWS Bedrock (EU region)**, xAI models via **xAI (EU)** for the Voice Agent |
| **Non-EU customers (including US)** | Models hosted **in the US** | OpenAI models via the **OpenAI platform**, Anthropic models via the **Anthropic platform**        |

* You can view the **active region** used by your organization under\
  **Account settings**.
* **AI features that rely on external LLMs can be globally disabled** in your account settings.
* When disabled, AI Features and Agents that depend on LLM reasoning will no longer process or transmit data externally.

<figure><img src="/files/B9cYrN3mBqlz05TRDWvV" alt=""><figcaption></figcaption></figure>

### Control & auditability

ilert AI is designed for **auditable and controlled automation**:

* All AI and Agent actions are logged and traceable.
* You have full control to enable or disable AI features globally.
* MCP connections use HTTPS with strict authorization (API keys or OAuth).

For data processing, sub-processors, certifications and other compliance documentation, see the [ilert Trust Center](https://docs.ilert.com/trust-center).

### Learn more

{% content-ref url="/pages/tZyqyr1iIBMkE5ozfhhj" %}
[AI Features](/ai-and-agents/ai-features.md)
{% endcontent-ref %}

{% content-ref url="/pages/8mQaJXsxvcgaZcLVV4FA" %}
[Agents](/ai-and-agents/agents.md)
{% endcontent-ref %}


---

# 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://docs.ilert.com/ai-and-agents/introduction.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.