The context layer for AI.
Atlan is the context layer for AI: the governed infrastructure delivering enterprise knowledge to every model, agent, and team from a single source of truth.
Context doesn't come from a prompt. It comes from a pipeline.
What is a context layer for AI?
A context layer for AI carries three things every agent needs before it can act:
- Knowledge: the data and assets an agent can trust, and where they came from.
- Semantics: what things in your business mean, and how they connect.
- Norms: how work actually gets done here, and what each agent is allowed to do.
See what makes a context layer work for AI → · Browse the context layer glossary → · Hear the ecosystem define it live at Context/26 →
AI agents reason over your enterprise without context.
17% → 42% scrapping AI before production, in one year.
Atlan · State of Enterprise Data & AI 2025A production context layer requires four things.
A context layer earns the name only when four capabilities hold together at runtime — not on paper, not in a roadmap deck.
A production context layer requires four things: unified coverage across every data system, canonical business semantics, governance applied by default, and continuous synchronization with the live data estate.
Without a context layer, AI agents hallucinate, contradict each other, and act on stale or unauthorized data; with Atlan, every agent reasons from the same governed truth.
- 1Unified coverage
Every data system, BI tool, and knowledge surface in scope. Nothing left dark. The Enterprise Data Graph powers Atlan's Data Marketplace, the catalog and governance surface.
- 2Canonical business semantics
One agreed model of what your terms mean, applied consistently wherever an agent or human queries them.
- 3Governance by default
Policy, authority, and access enforced at every query, every answer, every agent, not bolted on after the fact.
- 4Continuous synchronization
Stays current with the live data estate as schemas, owners, and definitions change. No stale snapshots, no drift.
Context to every agent.
Gold Layer context serves every agent through MCP, SQL, and APIs. Memory, evals, and traces feed back into the pipeline so context gets sharper with every interaction.
OCT 28, 2026 / 11:00 AM – 2:00 PM ET / VIRTUAL
The people building the context layer are speaking at Context/26.
Reference architectures, open AMAs, and peer roundtables with the AI leaders and architects building on open context. No sponsored slots, no product demos in disguise.
UPCOMING SESSION · SEP 2 · LIVE
WTF IS THE
CONTEXT LAYER?
Can a Context Graph Alone Make AI Reliable?
Sep 2 · 11 AM ET · Live
Jaya Gupta called the context graph AI's next trillion-dollar opportunity. What it left unsettled is whether a strong graph is enough alone, or whether reliable AI needs the context layer around it. Jaya joins Austin to work through what a context graph must hold and where it stops.
Jaya Gupta, Foundation Capital
Austin Kronz, Atlan
Already in production at AI-native enterprises.
Gartner Magic Quadrant Leader. Only 5/5 Forrester vendor, Deployment & Time-to-Value. Workday builds its semantic layer on Atlan. 8B context reads / 90 days.
"AI initiatives require more context than ever. Atlan's metadata lakehouse is configurable, intuitive, and able to scale to hundreds of millions of assets."
Atlan is the context layer for AI.
Let's build yours.
Context layer vs. data catalog vs. semantic layer vs. knowledge graph
Each earlier tool handled one slice of context. Only the context layer delivers governed definitions, lineage, and policy to AI agents at inference.
| Capability | Data catalog | Semantic layer | Knowledge graph | Context layer (Atlan) |
|---|---|---|---|---|
| Primary question it answers | What's in our stack? | What does a metric mean for BI? | What connects to what? | How should AI reason over this at inference? |
| Built for | Human discovery | BI dashboards | Entity relationships | AI agents at inference time |
| Delivered to agents at runtime | No | Metric definitions only | Structure only | Definitions, lineage, policy, and decision history |
| Governance enforced per query | No | No | No | Yes, scoped to the requesting user |
How does a context layer compare to a catalog or semantic layer?
A context layer delivers definitions, lineage, and governance to AI agents at inference. Earlier tools each solved one slice; the context layer unifies them.
vs. data catalog
A data catalog lists data assets like tables, owners, and descriptions for human discovery. It answers "what's in our stack?"
A context layer answers a different question: how should AI reason over those assets at inference? It adds decision history, runtime policy enforcement, and column-level lineage that agents query during a response. The catalog tells you a column exists. The context layer tells the agent what it means and whether the requester is authorized.
Atlan ships both: the catalog as the front door, the context layer as the engine.
vs. semantic layer
A semantic layer maps metrics to dashboards for BI tools and human analysts. Tableau, Looker, Mode all pull a "revenue" definition from one place so a chart matches the deck.
A context layer captures the full world model an agent needs: not just metric definitions, but the relationships between entities, the governance policies that apply for the user asking, and the authority record of who validated each piece. It serves that model through MCP from Atlan's Context Lakehouse to every agent in your stack, not just the BI layer.
Atlan's context layer treats the semantic layer as one input it ingests. Only the context layer can deliver definitions with the operational metadata an agent needs to cite its answer.
vs. knowledge graph
A knowledge graph captures entities and relationships: customer to order, order to product, product to inventory. The structure of what connects to what.
A context layer adds operational metadata to that structure: lineage, freshness, governed policies, decision history. The knowledge graph shows you the wiring; the context layer shows whether the wire is live, who certified it, and where it's authorized to flow.
Atlan's context layer ships the Enterprise Data Graph and the operational metadata together, served through MCP at inference. The answer arrives with the metadata baked in.
How does a context layer work for AI agents?
The context layer assembles definitions, lineage, policy, and provenance from the Context Lakehouse in one round-trip, then returns a grounded, cited answer.
The 7 steps in a context-layer trace
- Agent receives a question. A user asks the agent something concrete enough to require enterprise data: a metric, a timeframe, a population. The agent recognizes terms it doesn't itself define and needs governed context before it answers.
- Claude calls Atlan via Model Context Protocol. Instead of guessing, the agent reaches out to the context layer through MCP, the open standard for delivering structured context to AI. The request specifies which terms need resolution and which user is asking.
- Definitions resolved from the ontology. Atlan returns the canonical definitions from the Context Lakehouse: "net revenue" maps to a specific column in the finance schema, "enterprise customer" maps to a tier filter on CRM accounts. These are the definitions the data team certified, not the agent's best guess.
- Lineage validated. Before the agent uses a definition, the context layer traces source columns through every transformation. If the source is stale or the lineage is broken, the agent learns about it now, not after the wrong answer ships.
- Access policy checked. The user's role and entitlements are evaluated against every column in scope. PII fields get masked, region filters get applied, and the policy decision is recorded for audit.
- Query executed against your data. With the right definitions, validated lineage, and policy in hand, the query runs against the actual data warehouse. The context layer doesn't store your data; it directs how the agent reasons over it.
- Grounded answer returned with citations. The agent returns the answer and the sources behind it: which columns it used, which definitions it relied on, which policies were enforced. That's the difference between a plausible answer and a correct one.
In a context layer, the trace is: question → MCP call → definitions resolved → lineage validated → policy checked → query executed → grounded answer returned with citations. Skip any step and the agent is back to plausible answers.
Atlan's context layer ships as four products.
Context Lakehouse stores context on Iceberg. Enterprise Data Graph queries it by entity. MCP serves every agent runtime. Context Engineering Studio ships it.
Connect all your business systems and pull context across your data estate into one living graph.
AI teammates that document tacit knowledge and make your data AI-ready.
Version, test, and deploy the context your AI agents depend on, as code, in your CI.
The storage foundation purpose-built for context: a unified graph + file architecture on open formats, with vector search built in.
Common questions answered
No. A data catalog lists data assets like table names, owners, and descriptions, and is built for human discovery. A context layer is an active runtime that governs how AI reasons over those same assets at inference time, adding decision history, runtime policy enforcement, and lineage that agents query directly. The two are complementary, not interchangeable: the catalog tells you a column exists, the context layer tells the agent what that column means and whether the requester is authorized to use it. Atlan ships both: the catalog as the front door, the context layer as the engine.
Larger context windows let an agent read more tokens at once, but they don't tell the agent which definitions are certified, which lineage is current, or which policies apply to the user asking. A million-token window of raw documents is still a million unverified tokens. An agent that can't tell verified from unverified will confidently cite both. A context layer is the governed source those tokens draw from: it provides certified definitions, current lineage, and user-scoped policies that turn raw text into a trusted answer. Atlan's context layer makes a long-window model production-ready.
Model Context Protocol (MCP) is the open standard for delivering structured context to AI agents at inference. It's the wire connecting an agent to the source of truth when needed. The context layer gives MCP something governed to serve: verified definitions, lineage, policies, and decision history, assembled per request and user. Without one, MCP hands agents whatever loose context is available, and each assembles its ad-hoc version from raw data. Atlan is the source MCP serves: the Context Lakehouse holds the governed definitions, lineage, and policies that make MCP useful in production.
Atlan's context layer rolls out in four stages: Unify (connect warehouses, BI tools, and business systems), Bootstrap (Context Agents draft definitions, metrics, and ontology), Collaborate (humans certify the context), and Activate (certified context flows from the Context Lakehouse to every agent through MCP). Teams clear Unify and Bootstrap in days. Atlan AI Labs has measured a 5x accuracy improvement in agents grounded in this context, so the metric that matters isn't time-to-launch. It's the accuracy delta on the first high-risk agent.
A semantic layer standardizes metrics for human-built dashboards: a "revenue" definition lives in one place so every chart matches. Context grounding gets AI to the same standard. It pulls verified definitions, lineage, policies, and decision history into every AI answer at inference time, so an agent can cite its sources and explain why it's correct. The semantic layer is one input into context grounding, not a replacement. Atlan's context layer ingests the semantic layer into the Context Lakehouse, where governance, lineage, and authority bind to every metric an agent needs in production.
Stay in the loop on enterprise AI
Context & Chaos is Atlan's weekly Enterprise AI newsletter. Practitioner takes on context architecture, governance, and what's working in production.
Follow our Enterprise AI newsletter