A five-gate hallucination gateway
Every answer passes an ordered guard chain, freshness, ontology, validation, grounding and feedback, before it ever reaches a user. The control plane is the minimum viable deliverable, not a retrofit.
Microsoft AI agents in production
AI agents your risk team will actually approve.
Microsoft Fabric ships the agent. We deliver the governed layer that gets it past review: grounded answers that show their working, accuracy measured rather than asserted, and a trust report your risk function can read. On your data, in your tenant.
Shipped, live-proven on our internal capacity Microsoft Fabric Featured Partner
Ask Lisa governed agent
“What was net revenue in Q3 for the maritime division?”
£12.4M
verified against source
The Microsoft AI Agent Accelerator is Onyx Data's governed deployment of AI agents on Microsoft Fabric. Microsoft's first-party agents provide the engine; we deliver the governed layer that gets them into production, grounded answers traceable to source, accuracy measured through a verification harness, schema scoping and row-level security with FabOps, and a trust report your risk function can sign off. Delivered by Onyx Data, a Microsoft Fabric Featured Partner, on your data, in your tenant.
The agent gap
The engine is Microsoft's. The trust is the hard part.
Microsoft Fabric now ships first-party conversational agents over your data, the Fabric Data Agent and the Real-Time Intelligence Agent. The model is the easy part. An agent that invents a number, reaches data it should never see, or can't show how it got an answer will not survive a risk review, and never reaches production.
The governed layer
What we deliver around the agent
Answers that show their working
Every figure carries a verification flag, the literal SQL or KQL it ran, and the row count. Ambiguous questions get a clarify-first response; out-of-scope ones get a clean refusal.
Accuracy measured, not asserted
A scored grounding test set built for your data, run through a three-instrument harness, deterministic checks, an independent semantic judge, and numeric ground-truth verification, so the agent's accuracy on your estate is a number, not a claim.
Scoped by construction
Schema scoping at the serving layer plus row-level-security automation, the agent cannot ask for what it cannot see. PII and commercial columns are excluded before the agent is ever pointed at the data.
A trust report your risk function can read
Accuracy results, grounding coverage, refusal behaviour, residency considerations, and the honest bounds of a probabilistic system, the document that turns a demo into a deployment.
Your tenant, your capacity
Delivered governance-first by Onyx Data, a Microsoft Fabric Featured Partner. Your data never leaves your tenant; the deployment uses your Microsoft Fabric capacity and your Azure subscription.
Where it lives
Bound to where your people already work
- Microsoft Copilot StudioValidated for Microsoft Teams, with user identity carried through.
- Microsoft Foundry agentsThe path your business users reach, with least-privilege and trace evidence.
- Model Context Protocol endpointThe autonomous surface for your own AI systems, identity-aware by design.
FAQ
Questions buyers ask
What is the Microsoft AI Agent Accelerator?
It is Onyx Data's governed deployment of AI agents on Microsoft Fabric. Microsoft's first-party agents provide the engine; we deliver the governed layer that gets them into production, grounded answers traceable to source, accuracy measured through a verification harness, schema scoping and row-level security, and a trust report your risk function can sign off.
Does it use Microsoft's agents, or build a new one?
It uses Microsoft's first-party agents, the Fabric Data Agent and the Real-Time Intelligence Agent. We do not replace the engine; we add the governance, grounding and evidence around it that a risk function requires before go-live.
How do you stop the agent from hallucinating?
Every answer passes a five-gate gateway (freshness, ontology, validation, grounding and feedback) and carries its working, the literal query it ran and the row count, with a verification flag. Ambiguous questions get a clarify-first response and out-of-scope ones a clean refusal. Accuracy on your data is measured through a three-instrument verification harness, not asserted.
Where does our data go?
Nowhere. The deployment runs in your own Microsoft Fabric capacity and your Azure subscription; your data never leaves your tenant. Schema scoping and row-level security mean the agent cannot see data it should not.
Where can people use the agent?
Bound to where your people already work: Microsoft Copilot Studio (validated for Microsoft Teams), Microsoft Foundry agents, and a Model Context Protocol endpoint for your own AI systems, each with identity passthrough and least-privilege guidance.
Get a governed agent into production.
Book a 30-minute strategy call. We'll map the fastest route from a Fabric agent demo to a governed, risk-approved deployment on your estate.
Book a 30-Minute Strategy Call30 mins no pitch leave with a plan