Data catalogs were the context layer for data. Atlan is the context layer for AI.

Atlan connects your entire data estate, maps every dependency through lineage, and enriches every asset with AI-generated context. The result: an Enterprise Data Graph that every AI agent in your stack reads via MCP, A2A, or SQL — and every human finds in the Data Marketplace.
Book a Demo white arrowSee How It Works

The catalog solved the human problem. AI needed something bigger.

Data catalogs were built for a world where humans were the primary consumers of data. They made data findable, documented assets, tracked ownership. That was the right problem to solve.

AI changed the requirements entirely. AI agents don't browse — they need structured, machine-readable context served automatically, at scale, across every system and every protocol. That's not a catalog problem. It's a context infrastructure problem.

Atlan is the context layer for AI. Native connectors pull metadata from every system. Data Lineage maps column-level provenance automatically. Context Agents write the descriptions, definitions, and quality scores at 90%+ acceptance rate. The Enterprise Data Graph is the result: context infrastructure every AI agent reads and every human searches. One platform. The context layer for data. And for AI.

What We Believe

From the context layer for data to the context layer for AI.

The context layer starts where your data catalog does. And it goes much further.

The catalog collects

The catalog collects

Connectors pull metadata from every system in your stack — warehouses, pipelines, BI tools, SaaS apps, custom sources. Everything that produces data feeds the catalog automatically.

→ Native connectors for every source
Lineage connects it

Lineage connects it

Data Lineage reconstructs column-level provenance across every system. Quality signals, governance classifications, and business definitions propagate downstream automatically.

→ See how lineage works
Context Agents enrich it

Context Agents enrich it

Nine AI agents sit on top of the catalog and enrich it continuously — writing descriptions, building glossaries, scoring quality, classifying domains, and resolving metric conflicts. AI-generated. Human-certified.

→ Meet the Context Agents
Every agent and every human reads from it

Every agent and every human reads from it

The Context Lakehouse exposes the full context layer to AI agents via MCP, A2A, SQL, and REST. The Data Marketplace makes it searchable for humans in natural language.

→ Context Lakehouse→ Data Marketplace
TRUSTED BY $10T IN ENTERPRISE VALUE

Leading AI teams use Atlan to connect context

  1. Watch Video
    Sridher Arumugham
  2. Watch Video
    Kiran Panja
  3. Watch Video
    Andrew Reiskind
  4. Watch Video
    Mauro Flores
Item 1 of 4
Company logo
Company logo
Company logo
Company logo
COLLECT

Every system feeds the context layer. Automatically.

SETUP

Start building your context layer in 3 steps.

Atlan's connectors are built for everyone. Choose from OAuth or API credentials, select the scope, and set a schedule. That's it.

1

Authenticate your connection

Connect with OAuth or API credentials. Test your authentication before running so you can pre-empt failures, not debug them.

2

Scope what to bring in

Choose what to bring in at the database, schema, or table level.

3

Schedule and start ingesting

Set your crawl to run daily, weekly, or on-demand. Atlan handles incremental updates automatically so your context always reflects your current stack, with no manual maintenance required.

Authenticate your connection
INTEGRATIONS

Native connectors for every layer of your stack

CONNECT

Column-level lineage. Context that compounds.

Atlan reconstructs lineage from your SQL, pipelines, and APIs — so quality signals, governance classifications, and business definitions propagate to every downstream asset automatically.

HOW ATLAN BUILDS LINEAGE

The provenance layer your AI
reads before it acts.

Column-level provenance, reverse-engineered from your entire stack.

Lineage/SQL Parsing
SQL Query Parsed
CREATE TABLErevenue_aggASSELECT o.amountASnet_revenue, o.customer_id, d.regionFROMorders_raw oJOINdim_customers d ON o.customer_id= d.id
TABLE
✓
ORDERS_RAW
ANALYTICS / PROD
#amount
Acustomer_id
TABLE
✓
DIM_CUSTOMERS
ANALYTICS / PROD
Aregion
TABLE
✓
REVENUE_AGG
ANALYTICS / PROD
#net_revenue
Acustomer_id
Aregion
ENRICH

Nine AI agents. Every layer of context. 90%+ acceptance rate.

Context Agents enrich the context layer continuously — writing descriptions, building glossaries, scoring quality, and classifying domains. AI-generated at scale. Human-certified before it ships.

Scout
SCOUT
Ranks assets by what your team actually queries.
SUPERPOWERS
🔍Query Analysis
⚡Usage Signals
🛡️Asset Ranking
Scribe
WORKS BEST WITH
Scribe to prioritize what gets described first
Meet your team
ROLLOUT

Rollout in 30 days, not 12 months.

Start With What Matters

Start With What Matters

Most of your catalog nobody touches. Context Agents identify your Gold Layer, Popular BI, Popular SQL, and upstream dependencies first — enriching the assets people actually use before spending cycles on the long tail. Value shows up in days, not months.

AI Scores Every Output

AI Scores Every Output

Each agent output carries a composite confidence score across accuracy, clarity, style, and completeness. High-confidence outputs auto-apply. Lower-confidence outputs route to humans.

Humans Decide & Govern

Humans Decide & Govern

AI generates descriptions, classifies assets, builds metrics, and scores quality at scale. Stewards shift from documentation to certification — sampling, validating, and resolving the cases that require judgment. One click. Not 847 manual reviews.

DELIVER (AGENTS)

For AI agents: one context layer, every protocol.

AI agents don't browse — they read context. The Context Lakehouse exposes the full context layer to every AI agent in your stack via MCP, A2A, SQL, and REST.

PROTOCOL SUPPORT

One open store. Every protocol
AI agents speak. Built natively for AI.

Speaks every protocol AI agents use and every protocol humans already know.

Every interface an agent needs, and every interface a human already uses. From MCP for governed queries to SQL for analytics — Context Lakehouse meets your stack where it is.

Click any node to explore
Click any node
to explore context
"AI initiatives require more context than ever. Atlan's metadata lakehouse is configurable, intuitive, and able to scale to hundreds of millions of assets."
avatar

Andrew Reiskind

Chief Data Officer, Mastercard

logo
DELIVER (HUMANS)

For humans: search your data in plain language.

The same context layer that feeds your agents is searchable for humans — in natural language, SQL, or by business term. Access is governed automatically.

BUILT FOR ADOPTION

Ask your question, get your answer, access your data. Personal, governed, instant.

Struggling to drive adoption? Never again.

Traditional catalogs were built for data teams, not the rest of the organization. Clunky search, jargon-heavy interfaces, no trust signals. Atlan works the other way around: plain-English search, role-personalized results, and embedded in Slack and Teams.

Ask AI›What's our most trusted churn dataset?
+ New
✦
Reasoning ∨
✓Searching certified datasets matching 'customer churn'
🔍 certification = verified🔍 domain = customer
●Evaluating trust signals across 12 matching assets
🔍 freshness🔍 usage_count🔍 certification
✓Found highest-trust match
📊
Customer Churn Rate — Q1
Snowflake · customer_analytics.churn_rate
✓ CertifiedUpdated 47 min ago
Request Access
Ask a follow-up
"The UI was so intuitive that even first-time users could search, navigate and find what they needed. Within the first year after that we cataloged over 18 million assets, defined more than 1,300 glossary terms, and we are tackling new use cases every quarter."
avatar

Kiran Panja

MD, Cloud & Data Engineering, CME Group

logo
INDUSTRY RECOGNITION

The recognized leader in bringing the context ecosystem together

  1. Analyst chart

    "Users consistently praise Atlan''s ease of use, flexibility, and responsiveness. They highlight its intuitive UI, strong lineage and smart search capabilities, and seamless integration across the data stack. Atlan is a Customer Favorite in this evaluation."

    Forrester Customer Favorite · The Forrester Wave™: Data Governance Solutions, Q3 2025

    Read the Forrester report
  2. Analyst chart

    "Leveraging the metadata lakehouse, the Atlan App Framework provides a structured toolkit and a marketplace to help developers, customers, and partners build, deploy, and share a wide range of applications, including custom connectors, data quality apps, and governance agents."

    Leader in the 2026 Gartner® Magic Quadrant™ for Data & Analytics Governance Platforms · Visionary → Leader in one year

    Read the Gartner D&A report
  3. Analyst chart

    "Atlan''s Metadata Lakehouse forms the core foundation, built on an open and highly performant architecture. It is designed to be Iceberg native and includes a knowledge graph and event stream engine. Its core components also include a knowledge graph for business domains and vector storage & analytics, which is purpose-built for AI."

    Leader in the 2025 Gartner® Magic Quadrant™ for Metadata Management Solutions · #1 for enabling modern data architectures

    Read the Gartner MMS report
Item 1 of 3
Slide 1 of 3
EXPLORE THE PLATFORM

Every layer of the context layer for AI.

Context Agents

Context Agents

AI teammates that enrich your catalog automatically.

→ Context Agents
Data Lineage

Data Lineage

Column-level provenance across every system.

→ Data Lineage
Context Lakehouse

Context Lakehouse

Deliver context to every AI agent.

→ Context Lakehouse
Data Marketplace

Data Marketplace

Help every human find what they need.

→ Data Marketplace

Data catalogs were the context layer for data.
This is the context layer for AI.

Book a Demo

30-min call. An honest conversation

FAQ

Frequently Asked Questions: Data Catalog for AI Agents

Is Atlan a data catalog?

circle arrow up
Atlan is the context layer for AI — the infrastructure that makes every AI agent in your stack accurate, trustworthy, and production-ready. Data catalogs were the context layer for data: they made data findable for humans. Atlan is what comes next.

What's the difference between a data catalog and a context layer?

circle arrow up
A data catalog makes data findable for humans. A context layer makes AI agents accurate. The catalog was the right answer for the first problem. Atlan is the right answer for the second — building the Enterprise Data Graph automatically and delivering it to every AI agent via MCP, A2A, or SQL, and every human through the Data Marketplace.

How does Atlan deliver context to AI agents?

circle arrow up
Atlan's Context Lakehouse exposes the full Enterprise Data Graph to AI agents through every protocol they speak — MCP for LLM tools like Claude and Snowflake Cortex, A2A for multi-agent orchestration, and SQL for agents that already query data.

What is the Enterprise Data Graph?

circle arrow up
The Enterprise Data Graph is what Atlan's data catalog becomes when everything is automated. Connectors pull metadata from every system. Data Lineage reconstructs column-level provenance. Context Agents write descriptions, glossary terms, quality scores, and domain classifications — at scale, continuously. Every asset, every system, fully documented and machine-readable.

Can Atlan replace our existing data catalog?

circle arrow up
Yes. Atlan replaces your data catalog with the context layer for AI — connecting every system, documenting every asset through Context Agents, and mapping every dependency through Data Lineage, automatically. Everything your catalog was doing for humans, Atlan does for both humans and AI agents.
[Website env: production]