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 — 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.Documentation Index
Fetch the complete documentation index at: https://docs.elementary-data.com/llms.txt
Use this file to discover all available pages before exploring further.
Specialized agents
The Elementary AI Agent orchestrates a set of specialized agents, each focused on a specific workflow:Governance
Enriches metadata and enforces documentation standards across your data assets.
Triage & Resolution
Investigates incidents, traces root causes, and opens pull requests with proposed fixes.
Test Recommendation
Identifies coverage gaps and recommends or generates tests for the right assets.
Catalog
Surfaces data assets, their relationships, and usage context in natural language.
Performance & Cost
Detects slow or expensive models, flags redundant tests that slow down the pipeline, and suggests optimizations.
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.Context Engine
Understand what the agent knows and how it knows it.
AI Privacy Policy
How AI features are secured and what data is accessed.