Every new AI agent your team deploys starts from scratch: no memory of how the business works, where the data lives, or what rules apply. As agent coding tools spin up applications faster than anyone can manage them, each one risks becoming another silo completely outside your data layer. Microsoft is addressing both issues directly in Build 2026.
according to VentureBeat’s VB Pulse’s Q1 2026 RAG Infrastructure Market TrackerHybrid search intent among more than 100 employee organizations tripled from 10.3% in January to 33.3% in March, indicating that businesses are moving past the expanding RAG scope and are now focusing on the underlying architecture. Shared business context is an intractable part of search.
On the context side, Microsoft expands Fabric IQ, the existing business data context layer, into a broader unified system called Microsoft IQ, adding three additional sources of context that cover how the organization works, what it knows, and real-time global signals from the Internet, so any agent can tap into all four as a single foundation. On the application side, Rayfin, a new open-source SDK and CLI, deploys agent-built applications directly into Fabric as a managed production backend, routing application data to the same platform instead of creating new silos.
Amir Netz, CTO of Microsoft Fabric, used a movie analogy to explain where the data platform fits. Cascade code green screen "Matrix" It wasn’t the atmosphere, it was the layer that made up the world in which Agent Smith operated.
"Our job in the data world is to create a reality for data-driven agents." Netz told VentureBeat.
Microsoft IQ combines four context sources into a single agent pool
Microsoft IQ brings together the four sources of context, which until now existed separately, so that the developer can combine the new agent into four agents in one integration step.
Business IQ. It captures how the organization works day-to-day, using email, documents, meetings and schedules to give agents insight into people, teams and workflows.
Cast IQ. Manages institutional knowledge, curating and indexing knowledge bases so that agents understand what it means to work within the organization, what rules apply, and what procedures to follow.
Fabric IQ. Fabric models the live operational state of a business through data that defines entities, relationships and business rules based on real-time signals from Fabric Real-Time Intelligence. Ontologies, the layer that captures that operational context, are expected to reach GA in the coming months.
Web IQ. Adds real-time global context from the web, providing agents with a current view of the world outside the organization along with information inside the organization.
"Agents will be highly knowledgeable virtual workers," Netz said. "This is where the world is going."
Rayfin redirects the programs built by the agent to the same database
Creating a shared context solves half the problem. Another is what happens when agents start building apps. Every new application needs a backend, and without a controlled deployment path, each one creates a new data silo completely outside the context layer.
Rayfin provides an enterprise-grade backend and deploys agent-built applications directly into Fabric, so application data falls into Microsoft OneLake by default and is fed back into the Microsoft IQ context layer instead of being collected outside of it.
Microsoft is pitting Rayfin against Supabase and Neon, Postgres-compatible backends that agent coding tools implement by default. The differentiator is management: Instead of creating isolated silos, Rife guides the entire application fleet through a single data and compliance layer of the Fabric.
Netz characterized the relationship as two-way. The agent that creates the Rayf application uses the ontology of the organization. The data generated by the application then enriches this ontology for the next agent.
Every major data platform seeks the same answer, but its execution is unproven
Microsoft is not the only platform creating a shared context layer for agents. Snowflake announced This week’s contextual opportunities with semantic opportunities. Pine cone has the Nexus platform, which extends the vector database to become a knowledge engine, and is powered by Redis Iris context and storage platform.
Microsoft’s approach reinforces the trend that RAG and model availability are no longer an issue.
"Fabric IQ and Rayfin are important because the enterprise AI challenge is no longer just about model availability," KramerERP managing partner Robert Kramer told VentureBeat. "The real question is whether Microsoft is simplifying implementation and strengthening trust, or adding another layer to an already complex environment."
