> ## Documentation Index
> Fetch the complete documentation index at: https://elementary-devin-1782754750-bigquery-permissions-docs.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Elementary AI Agent

The Elementary AI Agent automates the workflows that slow data teams down most: finding coverage gaps, triaging incidents, fixing broken pipelines, enriching metadata, and optimizing query performance.

It's a single agent backed by the [Context Engine](/cloud/ai-agents/context-engine) — a continuously updated knowledge layer built from every integration you connect. Because it has full context across your stack, it can act on incidents, recommend tests, and surface insights without requiring you to pull together the picture manually.

Every action the agent takes goes through a pull request or requires explicit confirmation. Your team stays in control of what gets merged.

## Specialized agents

The Elementary AI Agent orchestrates a set of specialized agents, each focused on a specific workflow:

<CardGroup cols={3}>
  <Card title="Governance" icon="tags" href="/cloud/ai-agents/governance-agent">
    Enriches metadata and enforces documentation standards across your data assets.
  </Card>

  <Card title="Triage & Resolution" icon="toolbox" href="/cloud/ai-agents/triage-resolution-agent">
    Investigates incidents, traces root causes, and opens pull requests with proposed fixes.
  </Card>

  <Card title="Test Recommendation" icon="vial-circle-check" href="/cloud/ai-agents/test-recommendation-agent">
    Identifies coverage gaps and recommends or generates tests for the right assets.
  </Card>

  <Card title="Catalog" icon="book-open" href="/cloud/ai-agents/catalog-agent">
    Surfaces data assets, their relationships, and usage context in natural language.
  </Card>

  <Card title="Performance & Cost" icon="comments-dollar" href="/cloud/ai-agents/performance-cost-agent">
    Detects slow or expensive models, flags redundant tests that slow down the pipeline, and suggests optimizations.
  </Card>
</CardGroup>

## How it works

The agent runs on self-hosted models through Amazon Bedrock. No data leaves your environment, and all AI features are opt-in by default. Agent behavior is governed by AI policies you define — reviewable, adjustable, and aligned to your governance standards.

<CardGroup cols={2}>
  <Card title="Context Engine" icon="brain-circuit" href="/cloud/ai-agents/context-engine">
    Understand what the agent knows and how it knows it.
  </Card>

  <Card title="AI Privacy Policy" icon="user-lock" href="/cloud/general/ai-privacy-policy">
    How AI features are secured and what data is accessed.
  </Card>
</CardGroup>

<Tip>Want to learn more? [Our experts will be happy to chat.](https://meetings-eu1.hubspot.com/joost-boonzajer-flaes/intro-call-docs?uuid=64e4c20d-0ff3-4454-9387-c93b47afcee6)</Tip>