Every new AI agent your team deploys starts from scratch: there is no memory of how the business works, where the data resides, or what rules apply. And as agent coding tools spin applications faster than anyone can govern them, each runs the risk of becoming another silo outside of your data layer entirely. Microsoft is addressing both issues directly in Build 2026.
According VentureBeat’s VB Pulse Q1 2026 RAG Infrastructure Market TrackerHybrid recovery intent among organizations with more than 100 employees tripled from 10.3% in January to 33.3% in March, a sign that companies have moved beyond expanding RAG coverage and are now focusing on the underlying architecture. The shared business context is the part that recovery doesn’t solve.
On the context front, Microsoft is expanding Fabric IQ, its existing enterprise data context layer, into a broader unified system called Microsoft IQ, adding three additional context sources covering how the organization works, what it knows, and real-time global signals from the web, so any agent can leverage all four as a single foundation. On the application side, Rayfin, a new open source SDK and CLI, deploys agent-created applications directly to Fabric as a governed 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. The green screen of the cascading code in "The matrix" It wasn’t the atmosphere, it was the layer that built the world in which Agent Smith operated.
"Our job in the data world is to create reality for data-driven agents," Netz told VentureBeat.
Microsoft IQ unifies four context sources into a single agent foundation
Microsoft IQ brings together four previously separate context sources, designed so that a developer can connect a new agent to all four in a single integration step.
Work IQ. Capture how the organization operates day to day, drawing on emails, documents, meetings, and schedules to give agents an understanding of people, teams, and workflows.
Foundry IQ. Manage institutional knowledge, curating and indexing knowledge bases so agents understand what it means to work within the organization, what rules apply, and what procedures to follow.
Fabric IQ. Model the live operational state of the business through data, defining 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 arrive in GA in the coming months.
Web intelligence quotient. It adds real-time global context from the web, giving agents a current picture of the world outside the organization along with its internal data.
"Agents will become highly informed virtual employees," Netz said. "That’s where the world is heading."
Rayfin routes applications created by agents to the same database
Creating a shared context solves half the problem. The other is what happens when agents start generating applications. Every new application needs a backend, and without a governed deployment path, each creates a new data silo outside of the context layer entirely.
Rayfin provides an enterprise-grade backend and deploys agent-built applications directly to Fabric, so application data arrives in Microsoft OneLake by default and is fed back to the Microsoft IQ context layer instead of accumulating outside of it.
Microsoft positions Rayfin against Supabase and Neon, the Postgres-compatible backends that use agent coding tools by default. The differentiator is governance: Rayfin routes the entire application fleet through Fabric’s unified data and compliance layer instead of creating isolated silos.
Netz described the relationship as two-way. The agent that creates a Rayfin application is based on the organization’s ontology. The data generated by that application enriches that ontology for the next agent.
All major data platforms seek the same answer, but execution is unproven
Microsoft is not the only platform that creates a shared context layer for agents. Snowflake announced their own contextual capabilities this week with semantic capabilities. Pineapple has its Nexus platform that extends the vector database to become a knowledge engine and Redis has developed its iris context and memory platform.
Microsoft’s approach further reinforces the trend that RAG and model availability are no longer the problem.
"Fabric IQ and Rayfin are important because the enterprise AI challenge is no longer just about model availability," Robert Kramer, managing partner at KramerERP, told VentureBeat. "The real question is whether Microsoft simplifies execution and strengthens trust or adds another layer to an already complex environment."
