Semantic Intelligence is a key element of really understanding what data means and how it can be used.
Microsoft is now deeply integrating semantics and ontology Fabric Data Platform With its new Fabric IQ technology, which was introduced at the Microsoft Ignite conference on Tuesday.
Fabric IQ is a semantic intelligence layer designed to solve a fundamental problem with enterprise AI agents: Effectiveness depends not only on the size of the dataset, but also on how well the data reflects actual business operations. The new technology creates a shared semantic structure that maps datasets to real-world entities, their relationships, hierarchies, and operational context. The semantic layer represents the latest step in Microsoft’s data platform strategy, having recently integrated LinkedIn’s graph database Technology to provide context.
Microsoft is also expanding its data portfolio with a series of new services: Azure HorizonDB, a PostgreSQL-compatible service in early preview, as well as SQL Server 2025 and Azure DocumentDBwhich are now generally available.
"When I think about what Fabric does for customers, it gives customers a unified data platform so they don’t have to tie together many, many, many different tools to get business value," said Arun Ulag, corporate vice president of Azure Data at Microsoft.
Why does semantic understanding matter for AI agents?
Traditional AI agents struggle with a fundamental limitation: They can see patterns in data but do not understand what that data represents in a business context. An agent may analyze sales transactions without understanding customer hierarchy, seasonal patterns, or product relationships. It can query the inventory level without knowing how production lines connect to the distribution network or how supplier relationships affect availability.
This gap between raw data and business meaning leads to unreliable predictions and poor automated decisions. Ulag explained that Fabric IQ addresses this by providing a semantic layer that reflects how organizations actually work.
This architectural approach differs significantly from the retrieval-augmented generation (RAG) and vector database strategies that competitors have emphasized.
While RAG pulls relevant documents to provide context, Fabric IQ creates a continuous semantic graph representing organizational structure, workflow, and business logic. Agents do not simply retrieve information. They understand relationships such as which suppliers provide which products, how production lines connect to inventory systems or how customer hierarchies connect to sales territories.
From analytics semantic models to operational ontologies
Microsoft has invested in semantic models through Power BI for over a decade. These models encapsulate business logic and define entities and relationships; They specify metrics and hierarchy; And they connect to diverse data sources across SaaS platforms like Azure, AWS, Google Cloud, on-premises systems, and Dynamics 365.
"We have 20 million semantic models that run in Fabric today. Why? Because we have created a semantic modeling layer in Power BI. So behind every Power BI report is a semantic model," Ulag said. "These semantic models already encapsulate a lot of business logic that reflects what the customer cares about. What is the data they care about? What are the metrics they care about? How are the data related to each other?"
The limitation of these semantic models has been their scope. They worked well for business intelligence, analytics, and visualization, but they only worked for individual reports or within departmental boundaries. Fabric IQ removes these barriers.
"However, there has been a gap between us. These semantic models were used only for BI use cases," Ulag said. "There’s a huge opportunity there to be able to take these semantic models and upgrade them into full ontologies."
Upgrading the semantic model to an ontology fundamentally changes what organizations can do with business context and meaning. "What does it do if you upgrade them to Ontology? What happens is that you can now connect the data to your enterprise," Ulag said.
He explained that the ontology also integrates with real-time data streams. In addition to connecting data, ontologies allow organizations to define operational rules. This combination lays the foundation for operational agents that understand business context at a level that traditional AI systems cannot achieve. Cross-enterprise data connections work together with real-time integration and rule definitions.
Operational agents who understand and act on business operations
Fabric IQ enables a new class of Microsoft call agents "Operating Agent." These agents can autonomously monitor data and take actions based on the ontology’s understanding of business operations.
"We’re also introducing something called an Operations Agent in Fabric that can look at your data for you, that can look at the rules that you’re asking it to monitor. And it can take action autonomously under human supervision," Ulag said.
Ulag provided a supply chain example that illustrates the difference from the traditional approach. An organization can model its supply chain and distribution operations in an ontology. When real-time data shows congestion in part of a city, the operations agent can automatically reroute trucks around the problem.
Ontologies built into Fabric IQ integrate directly with Microsoft’s agent development platform. It provides business context that makes agents more reliable and accurate.
"It really takes the work we’ve done in semantic models with integrated data to a completely different level, allowing customers to be able to model their operations and take business actions," Ulag said.
What this means for enterprise AI strategies
It appears that a need for reference engineering To better enable agentic AI.
Semantics and their related ontologies do just that and more. Context is about understanding why the request is being made, and semantics is about understanding the deeper meaning. For enterprises struggling with AI agent reliability despite large datasets, Fabric IQ represents a fundamentally different approach. This goes beyond scaling compute or fine-tuning models. The key question is whether business context captured in the ontology will improve agent effectiveness more than traditional optimization paths.
The strategic bet Microsoft is making is clear: Semantic understanding of business operations determines the effectiveness of an AI agent. Access to large datasets alone is not enough. Upgrading existing semantic models to operational ontologies can provide a faster path to trusted agents.