> ## 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.

# Mistral AI

> Connect Rootly to Mistral AI to send prompts to Mistral models from incident and action item workflows for AI-assisted summaries, drafts, and triage.

## Introduction

The Mistral AI integration lets you connect Rootly to your organization's Mistral AI API account. Once connected, a new **Mistral Chat Completion** workflow action becomes available, allowing you to send prompts to Mistral models and capture their responses — directly within your incident and action item workflows.

With the Mistral AI integration, you can:

* Generate AI-powered incident summaries, analyses, and recommendations
* Send custom prompts to Mistral and Codestral models with full Liquid template support
* Use a system prompt to define the model's role, tone, or output constraints
* Control response style with temperature, max tokens, and nucleus sampling parameters

## Before You Begin

Before setting up the Mistral AI integration, make sure you have:

* A Rootly account with permission to manage integrations
* A [Mistral AI API key](https://console.mistral.ai/) with access to at least one model

<Callout icon="triangle-exclamation" color="#FEF3C7">
  Your API key is validated against the Mistral API when you save the integration. If validation fails, confirm the key is active and has not been revoked in the Mistral console.
</Callout>

## Installation

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

  <Step title="Enter your API key" icon="key">
    Paste your Mistral AI API key into the **API Key** field. Rootly validates the key by fetching your available models before saving. Your key is encrypted at rest in Rootly.
  </Step>

  <Step title="Integration connected" icon="circle-check">
    <Callout icon="circle-check" color="#DCFCE7">
      Your Mistral AI integration is active. The **Mistral Chat Completion** workflow action is now available in your incident and action item workflows.
    </Callout>
  </Step>
</Steps>

## Workflow Actions

### Mistral Chat Completion

Sends a prompt to a Mistral model and captures the response as a workflow output. The model list is fetched dynamically from your API account and includes `mistral-`, `codestral-`, and `open-` model families.

| Field         | Description                                                                | Required |
| ------------- | -------------------------------------------------------------------------- | -------- |
| Model         | The Mistral model to use — fetched from your account                       | 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 `1.5` — 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">
    Rootly validates your API key by fetching the list of available models when you save. If validation fails, confirm the key is active in the [Mistral console](https://console.mistral.ai/) and has not been revoked or restricted.
  </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 or revoked. Update the key in the integration settings — Rootly re-validates on save.
  </Accordion>

  <Accordion title="The workflow action fails with a rate limit error" icon="gauge-high">
    Mistral AI enforces rate limits based on your API tier. Running many concurrent workflows may exceed requests-per-minute limits. Consider staggering workflows, reducing token usage with more focused prompts, or upgrading your Mistral plan for higher quota.
  </Accordion>

  <Accordion title="A model is not appearing in the model selector" icon="robot">
    The model list is fetched dynamically from your API account and is filtered to `mistral-`, `codestral-`, and `open-` model families. If a model you expect is missing, confirm your API key has access to it — some models may require specific Mistral tiers or allowlisting.
  </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="Incident Workflows" icon="bolt" href="/workflows/incident-workflows">
    Build workflows that use Mistral 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>

  <Card title="Rootly AI" icon="robot" href="/ai/ai">
    Learn about Rootly's built-in AI features for incident management.
  </Card>
</CardGroup>