A business glossary tells humans what terms mean. Atlan's context layer gives AI agents the complete semantic picture.

Business glossaries were built for humans — a shared reference that told data teams what "active customer," "net revenue," or "churn" actually meant in this organization. Useful when maintained. Hard to keep current. And only one piece of what an AI agent actually needs to answer correctly.

AI agents need more than a glossary. They need to know what "revenue" means in Finance vs. Sales, and which definition applies to the question being asked. They need to know how a technical column name maps to the business term an analyst would use. They need to know that "MRR" and "monthly recurring revenue" are the same thing — and that the EMEA definition has a different treatment for professional services. And they need to know how all of those terms relate to each other: which metrics are derived from which definitions, which domains own which concepts, and where one term ends and another begins.

That's what a semantic layer is. That's what an ontology is. And Atlan's context layer includes all of it — not as separate tools that need to be integrated, but as a single, connected semantic picture that every AI agent reads from automatically.

Atlan's Context Agents — specialized AI teammates that build and maintain the semantic context layer automatically — each own a different piece of the picture. Lexis, the Glossary Bootstrapping agent, builds your business glossary from your existing definitions and domain patterns. Nexus, the Terms & Metrics Linkage agent, bridges technical column names to the business terms analysts actually use. Sage, the Metric Conflicts agent, finds where two teams define the same metric differently and locks in one certified answer. Orion, the Ontologist, maps every relationship between domains, terms, and assets — so when an agent asks what "revenue" means, it gets the right answer for the right context. All of it versioned, delivered to every agent through MCP, and connected through lineage so definitions travel with the data they describe.

Atlan's Context Agents each own a piece of the semantic picture — Lexis builds the glossary, Sage resolves metric conflicts, Nexus bridges technical and business language, Orion maps every relationship. Together, they give every AI agent the semantic context it needs to answer correctly.

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. No more agents working from conflicting versions of the truth.

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.