---
title: "Business Glossary | Atlan | Context Layer for AI"
url: "https://atlan.com/data-glossary/"
description: "Atlan's context layer gives AI agents a business glossary — and the full semantic picture beyond it: shared metrics, semantic definitions, and ontology, all connected through your data."
---

> Atlan is hosting Context Conference, bringing together the leaders and builders at the frontier of giving AI the context it needs to understand their business. It runs online on October 28, 2026, from 11:00 AM to 2:00 PM ET. Atlan co-founder Prukalpa Sankar opens and closes the day. Leaders from AstraZeneca, BNY and Verizon share why they invest in context and what they get from it. Registrants get early access to The AI Context Gap, a new study from MIT Technology Review Insights. Register: https://atlan.com/context-conference/

**A business glossary tells humans what terms mean. Atlan's context layer gives AI agents the complete semantic picture.** Atlan's context layer includes a business glossary for AI agents and goes further: shared business definitions, metrics resolved across teams, semantic definitions that connect technical columns to business meaning, and an ontology that maps how every term relates to every other. Delivered to every agent automatically.

[Book a Demo](https://atlan.com/forms/talk-to-sales-contact/) · [See How It Works](https://atlan.com/context-layer-demo/)

## A business glossary is where it starts

Business glossaries were built for humans: a shared reference for what "active customer," "net revenue," or "churn" meant in this organization. Useful when maintained, hard to keep current, and only one piece of what an AI agent needs to answer correctly.

AI agents need to know what "revenue" means in Finance vs. Sales and which definition applies to the question; how a technical column name maps to the business term an analyst would use; that "MRR" and "monthly recurring revenue" are the same thing and that the EMEA definition treats professional services differently; and how terms relate: which metrics derive from which definitions, which domains own which concepts, where one term ends and another begins.

That is a semantic layer and an ontology. Atlan's [context layer](https://atlan.com/context-layer/) includes all of it as a single, connected semantic picture every AI agent reads from automatically, not as separate tools to integrate.

Atlan's [Context Agents](https://atlan.com/context-agents/) each own a piece: **Lexis** (Glossary Bootstrapping) builds your glossary from existing definitions and domain patterns; **Nexus** (Terms & Metrics Linkage) bridges technical column names to business terms; **Sage** (Metric Conflicts) finds where two teams define the same metric differently and locks in one certified answer; **Orion** (Ontologist) maps every relationship between domains, terms, and assets. All of it versioned, delivered to every agent through [MCP](https://atlan.com/context-lakehouse/), and connected through [lineage](https://atlan.com/data-lineage/) so definitions travel with the data they describe.

## From the business glossary to the complete semantic context layer

- **Business glossary, bootstrapped automatically.** Lexis reads your existing definitions, column naming conventions, and domain patterns and builds the glossary your team never finished, from signals that already exist in your systems.
- **Business metrics, resolved across teams.** Sage locks in one certified answer where teams disagree; Nexus bridges technical column names and business terms. Agents get authoritative metrics, not two conflicting definitions of "MRR."
- **Ontology that maps every relationship.** Orion maps what every term means in every context and how every term, domain, and asset relates, so an agent asking what "revenue" means gets the right answer for the right team, region, and use case.
- **Connected through lineage, delivered through MCP.** Every definition, metric, and ontology relationship propagates along [Data Lineage](https://atlan.com/data-lineage/). Versioned context repos in [Context Engineering Studio](https://atlan.com/context-engineering-studio/) make the semantic layer human-editable and machine-readable. Every agent reads the same shared truth through Atlan's MCP Server.

## Leading AI teams use Atlan to connect context

Trusted by $10T in enterprise value. Customer videos: Sridher Arumugham (DigiKey: Context Readiness), Kiran Panja (CME Group: Context at Speed), Andrew Reiskind (Mastercard: Context by Design), Mauro Flores (Virgin Media O2: Context for All).

## Enrich: the agents that give AI agents a complete semantic picture

Lexis builds the glossary, Sage resolves metric conflicts, Nexus bridges technical and business language, Orion maps every relationship. The full team of nine:

| Agent | Role | What it does |
|---|---|---|
| Scout | Usage Intelligence | Ranks assets by what your team actually queries. |
| Scribe | Description Writer | Writes descriptions from SQL patterns and lineage. |
| Lexis | Glossary Builder | Builds your business glossary from column patterns. |
| Doc | Readme Author | Synthesizes signals into comprehensive dataset readmes. |
| Nexus | Terms Linker | Links every column to the business term analysts use. |
| Sage | Metric Arbiter | Finds conflicting metric definitions and locks one answer. |
| Atlas | Domain Classifier | Tags every asset with its business domain at scale. |
| Vera | Quality Scorer | Scores every critical asset on completeness and freshness. |
| Orion | Ontologist | Maps the ontology connecting every domain and metric. |

### The journey: data catalogs were built for humans who never documented them

- **The first copilot.** In 2023 Atlan launched the first AI documentation agent, Atlan AI. It wrote descriptions automatically, but accuracy was 75%: enough to show the vision, not to replace human work.
- **We hit a wall.** Accuracy at scale needed AI to access lineage, query history, usage patterns, and relationships between assets. Atlan stored all of that but AI couldn't use it, so Atlan rebuilt the foundation: the Context Lakehouse.
- **The new reality.** Context agents now outperform humans on quality; customers say agent-written descriptions are more accurate and complete than their teams' manual work. Acceptance rate today: **90%+**. AI descriptions applied: **350K+**.

Start your AI-readiness sprint: Context Agents can get you to AI readiness in 30 days. [Book a Strategy Session](https://atlan.com/forms/talk-to-sales-contact/)

### Rollout in 30 days, not 12 months

- **Start with what matters.** Context Agents identify your Gold Layer, Popular BI, Popular SQL, and upstream dependencies first, enriching the assets people use before the long tail.
- **AI scores every output.** A composite confidence score across accuracy, clarity, style, and completeness. High-confidence outputs auto-apply; lower-confidence outputs route to humans.
- **Humans decide and govern.** Stewards shift from documentation to certification: sampling, validating, and resolving cases that need judgment. One click, not 847 manual reviews.

## Versioned: one shared definition, every agent, always current

Context Engineering Studio stores your glossary in versioned, domain-scoped context repos, so definitions are human-editable and machine-readable. Every agent reads from the same repo; when a definition changes, every agent that uses it improves automatically.

Context bootstrapping: don't start building context on a blank page. The knowledge AI needs already exists in systems of record, SQL queries, BI dashboards, and communication threads. Context Engineering Studio reads it all, drafts a semantic layer, and lets domain experts refine it, so you ship in days, not months.

- **Context repositories.** Versioned, bounded, portable units of context any agent can consume. Context Repos are to enterprise AI what Git repos are to software.
- **Domain-scoped.** Finance's "revenue" and Sales' "revenue" can both be correct; each Context Repo is bounded to a specific domain or use case. No universal ontology that tries to be everything.
- **Human-readable, machine-consumable.** Domain experts edit in plain language; the underlying model is structured YAML any agent framework can parse (LangGraph, Cortex, Genie, or your own).
- **Git-like versioning.** Full history, branching, A/B testing, staged rollouts, rollbacks.

"Atlan captures Workday's shared language to be leveraged by AI via its MCP server. As part of Atlan's AI labs, we're co-building the semantic layer that AI needs." — Joe DosSantos, VP Enterprise Data & Analytics, Workday

## Connect: definitions that travel with your data

When a term is defined or updated in the glossary, that definition propagates along lineage to every downstream asset, so every AI agent querying those assets inherits the correct, certified definition automatically. A living graph that compounds everything:

- **Quality compounds along lineage.** When a quality check fails upstream, lineage shows every downstream dashboard, pipeline, and AI agent affected. Root cause analysis goes from days to minutes.
- **Governance propagates along lineage.** Tag a column as PII once; lineage propagates that classification downstream and syncs bi-directionally with Snowflake and Databricks.
- **Impact analysis travels along lineage.** Before a data engineer ships a change, Atlan shows the full blast radius inside the GitHub or GitLab pull request.
- **AI agents read the full context chain.** Through Atlan's MCP Server, an agent checking a column gets back provenance, quality score, governance policy, and ownership in one call.

## Industry recognition

- **Leader, 2026 Gartner® Magic Quadrant™ for Data & Analytics Governance:** "Atlan stands out in AI-native governance through context-based partnerships, agentic stewardship and orchestration of enterprise agentic systems. The underlying metadata lakehouse architecture boosts performance, scalability, extensibility and time travel auditability." [Report](https://atlan.com/gartner-magic-quadrant-data-governance-2026/)
- **Leader, 2025 Gartner® Magic Quadrant™ for Metadata Management Solutions:** "Atlan's solution focuses on automation, allowing every action to be performed programmatically via APIs and calling via an LLM. Its core components also include a knowledge graph for business domains and vector storage & analytics, which is purpose-built for AI." [Report](https://atlan.com/gartner-magic-quadrant-metadata-management-solutions-2025/)
- **Leader, The Forrester Wave™: Data Governance Solutions, Q3 2025:** "Atlan offers features that are among the best in class for policy management, stewardship, and collaborative governance. Its knowledge graph and AI-powered automation support clear data ownership, surfacing policy-relevant context and automating governance workflows." [Report](https://atlan.com/know/forrester-wave-data-governance-2025/)

## Explore the platform

- [Context Agents](https://atlan.com/context-agents/): glossary bootstrapping and metric conflict resolution at scale.
- [Context Engineering Studio](https://atlan.com/context-engineering-studio/): versioned definitions delivered to every agent.
- [Data Lineage](https://atlan.com/data-lineage/): definitions that propagate automatically to every downstream asset.
- [Data Marketplace](https://atlan.com/data-marketplace/): help every human find and use the right definitions.

## FAQ: business glossary

**What does a business glossary have to do with AI agents?**
AI agents don't resolve definition disputes by asking a colleague; they use whatever definition they find first. When Finance and Sales define "revenue" differently, agents querying both produce conflicting answers. When "active user" was redefined six months ago but old dashboards weren't updated, agents answer differently depending on which assets they touch. A business glossary is the shared vocabulary every agent needs; Atlan builds and maintains it automatically and delivers it through the context layer.

**How does Lexis build the business glossary?**
Lexis reads your existing definitions, column naming conventions, and domain patterns across your data estate and constructs your glossary from them, without starting from a blank page. Outputs are AI-generated at scale and human-certified before they ship.

**How does Sage resolve metric conflicts?**
Sage finds where two teams define the same metric differently ("MRR" in Finance vs. Sales, "active user" in Product vs. Marketing) and routes each conflict to the relevant stewards. Once a definition is approved, Sage updates it in the glossary and every AI agent that uses it inherits the certified answer.

**How do shared definitions reach AI agents automatically?**
Definitions live in versioned context repos inside Context Engineering Studio. Every AI agent reads from those repos through Atlan's MCP Server. When a definition is updated, by Lexis, Sage, or a human steward, every agent that uses it improves automatically. No manual distribution.

**What's the difference between a business glossary and the semantic context layer?**
A glossary defines terms. The semantic context layer gives AI agents everything they need to use those terms correctly: the glossary, business metrics resolved across teams, semantic definitions that bridge technical column names to business language, and an ontology mapping how every term relates across domains and contexts. Atlan's context layer includes all of it, connected through lineage and delivered through a single MCP server.

Four Context Agents, one complete semantic picture, connected through lineage and delivered to every agent through MCP. [Book a Demo](https://atlan.com/forms/talk-to-sales-contact/) (30-min call).