> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rootly.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Azure OpenAI

> Connect Rootly to Azure-hosted OpenAI deployments for AI-assisted incident workflows under your own compliance and data residency rules.

## Introduction

The Azure OpenAI integration lets you connect Rootly to AI models running inside your organization's Azure subscription. Rather than using Rootly's default OpenAI account, requests are routed through your own Azure OpenAI resource — giving you control over data residency, compliance posture, content filtering policies, and the specific model deployment your team has provisioned.

With the Azure OpenAI integration, you can:

* Generate AI-powered summaries, analyses, and responses within incident workflows
* Send custom prompts to your Azure-deployed GPT models with full Liquid template support
* Use a system prompt to define the model's role, tone, or output constraints
* Satisfy data residency and enterprise compliance requirements by keeping requests within Azure infrastructure

## Before You Begin

Before setting up the Azure OpenAI integration, make sure you have:

* A Rootly account with permission to manage integrations
* An active [Azure OpenAI resource](https://portal.azure.com) with at least one model deployed
* Your Azure OpenAI **API key**, **resource name**, and **deployment name** (details below)

<Callout icon="triangle-exclamation" color="#FEF3C7">
  Azure OpenAI resources are not automatically created with your Azure subscription. You must request access and deploy a model in the Azure Portal before connecting to Rootly.
</Callout>

### Finding Your Credentials

**API Key**

1. Go to the [Azure Portal](https://portal.azure.com) and open your Azure OpenAI resource.
2. Select **Keys and Endpoint** from the left menu.
3. Copy either **KEY 1** or **KEY 2**.

**Resource Name**

Your resource name is the subdomain portion of your Azure OpenAI endpoint URL. For example, if your endpoint is:

```
https://my-company-openai.openai.azure.com/
```

Your resource name is `my-company-openai`.

**Deployment Name**

1. In the Azure Portal, open your Azure OpenAI resource.
2. Select **Model deployments** or **Deployments** from the left menu.
3. Copy the name of the deployment you want Rootly to use (for example, `gpt-4o` or `gpt-35-turbo`).

## Installation

<Steps>
  <Step title="Open the integrations page in Rootly" icon="plug">
    Navigate to the integrations page in your Rootly workspace and select **Azure OpenAI**.
  </Step>

  <Step title="Enter your credentials" icon="key">
    Enter your **API Key**, **Resource Name**, and **Deployment Name** into the respective fields. Rootly constructs your Azure OpenAI endpoint as:

    ```
    https://{resource_name}.openai.azure.com/openai/deployments/{deployment_name}
    ```

    Your API key is encrypted at rest in Rootly.
  </Step>

  <Step title="Save and connect" icon="circle-check">
    <Callout icon="circle-check" color="#DCFCE7">
      Your Azure OpenAI integration is active. The **Create OpenAI Chat Completion** workflow action is now available in your incident and action item workflows, routing requests through your Azure deployment.
    </Callout>
  </Step>
</Steps>

## Workflow Actions

### Create OpenAI Chat Completion

Sends a prompt to your Azure-deployed model and captures the response as a workflow output. This is the same action used by the standard OpenAI integration — when Azure OpenAI is connected, Rootly routes requests through your Azure resource automatically.

| Field         | Description                                                                | Required |
| ------------- | -------------------------------------------------------------------------- | -------- |
| Model         | Your configured Azure deployment — set by the deployment name you provided | Yes      |
| Prompt        | The user message — supports Liquid templating                              | Yes      |
| System Prompt | Instructions for the model's role or behavior — supports Liquid templating | No       |
| Temperature   | Sampling temperature between `0.0` and `2.0` — controls randomness         | No       |
| Max Tokens    | Maximum number of tokens in the response                                   | No       |
| Top P         | Nucleus sampling probability between `0.0` and `1.0`                       | No       |

<Callout icon="code" color="#EDE9FE">
  Use Liquid variables in your prompts to include live incident context — for example `{{ incident.title }}`, `{{ incident.severity }}`, and `{{ incident.description }}`. See the [Liquid variables reference](/liquid/incident-variables) for all available fields.
</Callout>

The **System Prompt** field sets the model's persona or output format — for example: *"You are an incident response assistant. Respond in bullet points. Be concise."*

## Troubleshooting

<AccordionGroup>
  <Accordion title="The API key is rejected on save" icon="key">
    Confirm that the API key is active and has not been revoked. In the Azure Portal, go to **Keys and Endpoint** and verify the key is still valid. Also confirm that the resource name matches the Azure OpenAI resource the key belongs to — using a key from a different resource will cause authentication to fail.
  </Accordion>

  <Accordion title="The workflow action fails with an authentication error" icon="lock">
    If the integration was working and then stopped, the API key may have been rotated in Azure. Update the key in the integration settings. Also check that the deployment name has not been renamed or deleted in the Azure Portal.
  </Accordion>

  <Accordion title="The workflow action fails with a rate limit error" icon="gauge-high">
    Azure OpenAI enforces rate limits based on your provisioned capacity (tokens per minute and requests per minute). Running many concurrent Rootly workflows may exceed these limits. Consider staggering workflows, reducing token usage with more focused prompts, or increasing your Azure OpenAI quota in the Azure Portal.
  </Accordion>

  <Accordion title="The model is not responding as expected" icon="robot">
    The model behavior is determined by the deployment you configured — Rootly uses your deployment name directly and does not select a model. If you need a different model, create a new deployment in the Azure Portal and update the deployment name in Rootly.
  </Accordion>

  <Accordion title="Liquid variables are not rendering correctly in the prompt" icon="code">
    Check your Liquid syntax — unclosed tags or undefined variables can cause rendering failures. Use the [Liquid variables reference](/liquid/incident-variables) to confirm variable names and test your template in a low-stakes workflow first.
  </Accordion>
</AccordionGroup>

## Related Pages

<CardGroup cols={3}>
  <Card title="OpenAI" icon="robot" href="/integrations/openai">
    Use Rootly's standard OpenAI integration if you don't need Azure-specific data residency or compliance controls.
  </Card>

  <Card title="Incident Workflows" icon="bolt" href="/workflows/incident-workflows">
    Build workflows that use Azure OpenAI models to analyze, summarize, or respond to incidents.
  </Card>

  <Card title="Liquid Variables" icon="code" href="/liquid/incident-variables">
    Reference for all incident variables available in Liquid-templated prompts.
  </Card>
</CardGroup>