← Back to Technical Guides
Duczer East Guides: The semantic layer, explained for AI on enterprise data
AI & Data Engineering

The semantic layer, explained for AI on enterprise data

A governed set of business definitions that makes AI answers traceable and controlled
Guide AI & Data Engineering 9 min read October 29, 2026 Duczer East Insights
Part of the Insights topic: Semantics, RAG & Data Meaning →

A semantic layer is a governed set of business definitions that sits between your data platform and the people, reports and AI systems that use it. It says what "active customer", "net written premium" or "days past due" means, how each is calculated, which tables it comes from and who may see it. Every tool then asks for the metric by name instead of rebuilding it in SQL. For AI on enterprise data, that is the difference between an answer you can defend and one you cannot. This guide is part of our Semantics, RAG & Data Meaning series.

What a semantic layer is

Most firms already have the problem a semantic layer solves. Finance reports one number for deposits, risk reports another, and the branch dashboard shows a third. Each is correct by its own logic. The logic lives in three places, written three ways, and nobody can say which is right without a meeting.

A semantic layer moves that logic into one shared definition. It maps physical tables and columns to business terms, defines how measures are calculated, sets how entities join, and records who owns each definition. Reports, notebooks, applications and AI agents all query through it. Change the definition once and every consumer gets the change.

The idea is not new. BI tools have carried semantic models for decades. What changed is where the layer lives and who uses it. It used to sit inside one BI tool. Now firms want one layer that serves every BI tool, every application and every AI system, which is why the term "universal semantic layer" appears in vendor material.

Why AI needs a semantic layer

A language model asked "what were our deposits last quarter?" has to guess. It has to pick a table, decide which accounts count, choose a date field, and handle currency and closed accounts. It will produce SQL that runs. It may not produce the number finance reports.

A semantic layer removes the guessing. The model, or the agent wrapping it, asks for the metric "total deposits" for "last quarter" and the layer generates the query from the approved definition. Three things follow:

The same logic applies to retrieval. A retrieval system that pulls documents about "exposure" gets better results when it knows which of five meanings of exposure the user intends. Shared definitions help the retrieval side as much as the query side.

Semantic layer vs data catalog vs ontology vs knowledge graph

These four terms overlap, and vendors use them loosely. In practice they do different jobs.

Semantic layerData catalogOntologyKnowledge graph
Main jobDefine and compute business metrics consistentlyFind and describe data assetsDefine concepts and how they relateStore facts about real entities and their relationships
Answers"What is net written premium, and what was it last month?""Which tables hold policy data, and who owns them?""Is a guarantor a kind of counterparty?""Which companies does this borrower control?"
ContainsEntities, joins, measures, dimensions, access rulesMetadata, owners, lineage, classifications, glossaryClasses, properties, rulesNodes and edges with properties
Used byBI, applications, AI agents querying numbersData teams, stewards, auditorsModelers, reasoning systems, integrationSearch, fraud and KYC analysis, AI retrieval
Typical formYAML or SQL definitions, a query engineA catalog productOWL or RDF files, or a modeling toolA graph database
Examplesdbt Semantic Layer, Cube, AtScale, Snowflake semantic views, Databricks metric viewsApache Atlas, Collibra, Alation, Unity CatalogFIBO for financial servicesNeo4j and other graph databases

They work best together. The catalog says where data is and who owns it. The ontology fixes what the business concepts mean. The semantic layer turns those meanings into calculations. A knowledge graph holds the connected facts that tables represent poorly, such as ownership chains or referral networks.

What goes into a semantic layer

Whatever the product, a semantic layer holds the same kinds of definitions:

A metric definition usually looks something like this. The syntax below is illustrative, not any one product's format:

yaml
metric:
  name: total_deposits
  label: Total deposits
  description: End-of-day balance of open deposit accounts, in USD.
  owner: finance-data@bank.example
  entity: account
  measure:
    expression: sum(balance_usd)
    filters:
      - account_status = 'open'
      - product_family = 'deposit'
  time_dimension: balance_date
  dimensions: [region, product_line, customer_segment]
  access:
    roles_allowed: [finance, treasury, risk]
    row_policy: region_scope

The value is not the syntax. It is that the definition is versioned, reviewed and owned, like code. When a regulator asks how a reported figure was produced, you show this file and its change history.

Where the semantic layer lives

There are three common places to put a semantic layer. Most estates end up with more than one, which is why portability matters.

Inside the BI tool. Looker's LookML and Power BI semantic models are long-standing examples. They work well when one BI tool dominates. They serve other tools and AI agents less well.

Inside the data platform. Snowflake semantic views store logical tables, relationships, facts, dimensions and metrics as schema objects, and Snowflake's Cortex Analyst and Cortex Agents use them to generate SQL. Databricks metric views in Unity Catalog let you define a metric once and query it from SQL, dashboards, Genie and external BI tools. This keeps definitions next to the data and under the platform's access controls.

As a separate layer. The dbt Semantic Layer, powered by MetricFlow, along with Cube and AtScale, sits between platforms and consumers. This suits firms with several data platforms or several BI tools.

On Cloudera, the same pattern applies to Iceberg tables, with Apache Atlas recording lineage and access policy enforced in the platform. For firms that keep AI inside their own perimeter, the semantic layer is part of private AI on Cloudera, so models query governed definitions without data leaving the environment.

Portability is improving. The Open Semantic Interchange (OSI), started in 2025 by Snowflake, Salesforce, dbt Labs and others, publishes a vendor-neutral format for exchanging semantic models. dbt Labs released MetricFlow under the Apache 2.0 license as part of that work, and in 2026 the project entered the Apache Incubator as Apache Ossie. It is early, but it reduces the risk of locking definitions into one product.

Ontologies and knowledge graphs for regulated data

A semantic layer handles numbers well. It handles meaning across systems less well. That is where ontologies come in.

Financial services has a head start. FIBO, the Financial Industry Business Ontology, is maintained by the EDM Council, standardized through the Object Management Group, and written in OWL. It defines concepts such as legal entities, contracts, securities and loans, and how they relate. Firms rarely adopt all of it. They use the parts that match their domain as a reference, so that "counterparty" in the risk system and "counterparty" in the KYC system mean the same thing.

Healthcare has its own reference vocabularies, such as clinical terminologies for diagnoses and procedures, and the same principle applies: map local codes to a shared reference before AI reasons over them.

A knowledge graph stores facts using those concepts. In KYC, a graph that links people, companies, addresses and accounts shows ownership chains that would take many joins to find in tables. An AI agent investigating an alert can then walk the graph and cite each link it used.

None of this works without a catalog and lineage underneath. Definitions must point at real, governed data. Our page on data governance for regulated firms covers the catalog, lineage and access policy this depends on.

Before you buy a context graph

Vendors now pitch "context graphs" that mine the decision threads in chat, email and ticketing tools for the why behind enterprise activity. The idea is sound: systems of record capture what happened, and agents that only see the what will keep producing confident nonsense. Before funding one, ask three questions. Who owns the graph? Where does entity resolution happen? What does your context look like the day the vendor is acquired? A graph that sits as a thin layer over data you already store can add lock-in, new governance questions and an entity resolution problem nobody scoped.

Connecting AI agents to the semantic layer

An agent should ask the semantic layer for metrics, not write raw SQL against production tables. Two developments make that practical.

First, semantic layers now expose interfaces built for AI. Snowflake's Cortex Analyst reads semantic views. Databricks Genie reads metric views. The dbt MCP server lets AI assistants list and query Semantic Layer metrics through the Model Context Protocol (MCP), either self-hosted or as a service.

Second, MCP gives agents one standard way to reach those tools. That also gives you one place to control them. Route agent calls to the semantic layer through an AI gateway that checks the agent's identity, applies policy and logs every query. The log then records which agent asked for which metric, under which definition version, on whose behalf.

Two rules keep this safe:

Building a semantic layer: six steps

  1. Pick the questions first. Start with the 20 to 30 metrics that drive real decisions or regulatory reports, not every column in the warehouse.
  2. Name an owner for each metric. Usually a business owner, with a data engineer accountable for the implementation.
  3. Write the definitions, including the edge cases. Closed accounts, reversals, currency, late-arriving data. Most disputes live in the edge cases.
  4. Reconcile against current reports. Run each metric and compare it with the number finance or risk publishes today. Explain or fix every difference before anyone relies on it.
  5. Put definitions under version control and review. Treat a definition change like a code change, with tests and approval.
  6. Connect consumers one at a time. BI first, then applications, then AI agents, each through the layer rather than around it.

What auditors and examiners check

Reviewers do not ask whether you have a semantic layer. They ask whether reported numbers and AI answers are traceable and controlled. Expect requests like these:

If you can produce each of these from system records, AI answers built on the layer are ready for review.

When to bring in a partner

The technology choice is the easy part. The hard part is agreeing definitions across finance, risk and operations, reconciling them to reported numbers, and wiring AI agents to use them without bypassing controls. Duczer East provides data and AI consulting for regulated enterprises, including the semantic layer, ontology and knowledge graph that AI answers depend on.

Frequently asked questions

What is a semantic layer in simple terms?

A semantic layer is a shared dictionary of business definitions that tools and AI use to query data. It says what each metric means and how to calculate it, so every report and agent gets the same answer to the same question.

What is the difference between a semantic layer and a data catalog?

A data catalog helps you find and describe data, while a semantic layer defines and computes business metrics. The catalog says which tables hold policy data and who owns them. The semantic layer says what net written premium is and calculates it.

Is a semantic layer the same as an ontology?

No. An ontology defines business concepts and how they relate, while a semantic layer turns those concepts into calculations over specific tables. Many firms use an ontology, such as FIBO in financial services, as the reference that semantic layer definitions follow.

Why do AI agents need a semantic layer?

AI agents need a semantic layer so their answers match approved definitions instead of the model's guess. Without it, an agent writes its own SQL and may count the wrong accounts or dates. With it, the agent asks for a named metric, and the answer is traceable and access-controlled.

Do I need a separate semantic layer tool?

Not always. If most of your data sits on one platform, the platform's own semantic features, such as Snowflake semantic views or Databricks metric views, may be enough. A separate layer, such as the dbt Semantic Layer, Cube or AtScale, makes more sense with several platforms or BI tools.

What is the Open Semantic Interchange?

The Open Semantic Interchange is an open, vendor-neutral format for exchanging semantic model definitions between tools. Snowflake, Salesforce, dbt Labs and others started it in 2025, and in 2026 it entered the Apache Incubator as Apache Ossie.

Would you like to discuss semantic layers for your AI systems?

Duczer East provides Data and AI consulting for regulated enterprises, including the semantic layer, ontology and knowledge graph that AI answers depend on.

Prefer email? info@duceast.com
Duczer East — Where Data Engineering Meets Agentic AI

The Practitioner's Briefing

Senior-level insights on agentic AI, data engineering, and enterprise integration — delivered to your inbox.