2026年5月29日
For catalog owners, the job is to mirror those semantics large language models into the catalog and prevent siloed metric definitions from proliferating across multiple BI stacks. If a vendor claims a semantic layer but can’t show you the actual model files (schema, ontology, or metric definitions), they’re hand-waving. Ontologies and knowledge graphs live closer to semantic databases or graph stores (RDF triple stores, property graphs) that support inference, reasoning, and global identifiers across domains. A semantic layer is therefore not a nice-to-have; it’s the backbone that makes multi-BI, AI, and data mesh architectures trustworthy. If you’re building toward an agentic future on Databricks, this is a practical place to start.
- These are the teams running semantic layers in production, with deep insights into governance, adoption, and AI readiness.
- In the future, AI will not only query semantic models but also help create and maintain them.
- SML provides AI with a structured way to propose, refine, and ultimately help build semantic models programmatically.
- AI systems need a universal semantic layer to eliminate ambiguity and deliver deterministic answers.
- Within the AI stack, the semantic layer acts as the bridge between raw data and AI applications, providing the business context needed for accurate analytics, AI agents, and decision-making.
The semantic layer serves BI and AI analytics; the semantic database supports reasoning and cross-system identity. With a coherent semantic layer architecture and a strong catalog, you can support data mesh, multi-BI, and AI agents—without sacrificing trust in the numbers. If you see yourself in the multi-platform or data mesh scenarios described here, it’s worth exploring an integrated universal semantic layer. In 2026, your ability to deliver trustworthy analytics and AI depends on building a robust semantic data layer and aligning it with your catalog and Limitations of Semantic Layers for Enterprise AI Context governance strategy.
AtScale’s semantic models are defined in YAML, plain code. generative AI Review every client account in one conversation and share a roll-up report with your team. Speed up agency client reporting with Databox’s AI Analyst.
- LookML (Looker Modeling Language) helps you create the semantic model that empowers your organization to define the structure of your data and its logic, and abstracts complexity, easily connecting your users to the information they need.
- Beyond consistency, Looker’s semantic layer, powered by LookML, is a solid line of defense for data governance.
- It’s the essential tool that takes messy data and transforms it into the clean, consistent and governed context required for trustworthy, accurate, and truly intelligent AI.
- The AI agent doesn’t need to try to figure this out on its own because it’s already been deterministically defined in the LookML.
- By doing so, the semantic layer offers a foundation for generative AI tools to interpret business logic, not simply raw data, meaning answers are accurate, thanks to critical signals that map to business language and user intent, reducing ambiguity.
- Looker provides a single source of truth, ensuring data accuracy and delivering trusted business logic for the entire organization and all connected applications.
What are the different types of semantic layers?
Cube then layers on top, ingesting that metadata to build a semantic model with reusable metrics, dimensions, and pre-aggregations. Semantic layer architecture choices shape your ability to enforce governance, support AI, and avoid vendor lock-in. You can watch the Coalesce and Cube integration demo https://aicurated.com/ to see this universal pattern in action. This pattern is especially valuable when you operate in a multi-BI, multi-platform environment, or you are pursuing data mesh and want domain-aligned semantic models that still share global metrics.
• Semantic definition layer — AtScale defines and governs semantic models using SML (YAML-based, version-controlled, portable). Within minutes, Agent Bricks had access to the semantic models, could list them, inspect their metadata, and run queries. This significantly reduces the manual effort traditionally required to build and maintain semantic models. Because LLMs are good at writing code, we were able to generate a new semantic natural language processing model automatically from an existing Databricks table.