Work IQ MCP: fewer tools, more paths
Learn to discover paths, inspect schemas, and read messages with Work IQ MCP. A read-only example shows why fewer tools do not remove access, coverage, and authorization boundaries.
Microsoft IQ: four layers, four questions
The slide had a single box labeled Microsoft IQ, and the relationship manager's agent got one question right out of four. Microsoft IQ is the name of a set: Work IQ, Fabric IQ, Foundry IQ and Web IQ, each with its own question, data home, status per component, identity and boundary. This article maps the four layers: what is GA and what is in preview, who answers in each one, where they meet and how far the data goes.
Azure AI Content Safety: how to stop indirect prompt injection
The user prompt was clean. The hostile instruction came in through the content the tool brought back — and that is the door almost no security review looks at. This article gathers what moved in the 2026 OWASP Top 10, the two Prompt Shields intervention points, the spotlighting that ships off by default, what the MCP specification protects and what it leaves to you — and shows what has to be in place so a successful injection does not become impact.
Fabric data agent: five sources, 25 rows and English only
Five sources per agent, answers capped at 25 rows by 25 columns, documented support for English only, and read-only queries: the Fabric data agent has an entry contract no prompt renegotiates. This article gathers the six source categories, the output limits, the asking user's identity, and the two retirements of 26 August — and shows what has to be in place before the pilot becomes a commitment to the business.
A reranker cannot fix what search never retrieved: retrieval quality in RAG
When a RAG agent answers wrong, the model is rarely at fault: the right passage never reached the context. This article splits retrieval into three budgets that fail for different reasons — recall, precision, and passage context — and shows what fixes each one: structure-aware chunking, hybrid search with rank fusion, second-stage reranking, and retrieval measured separately from the answer.
A2A in production: delegating work does not transfer trust
A2A connects independent agents; MCP connects tools and resources. Understand tasks, identity, and trust across delegation, then follow a complete Python example to deploy and call an A2A agent in Microsoft Foundry, with RBAC and explicit preview limitations.
The vector index inherits no permissions: data agents on Databricks, Fabric and Foundry
A vector index is a copy, and a copy inherits no permissions: the Databricks AI Search documentation states that row and column level permissions are not supported. The two routes an agent takes to the data — RAG and text-to-SQL —, where the access rule lives on each one, the Genie Agent's two credentials, and the metric layer that stops the number from changing.
Guardrails and agent evaluation: what separates a demo from a production system
Guardrails contain at runtime; evaluation measures over time — and neither does the other's job. Content Safety, Prompt Shields, evaluators that see the tool call and not just the answer, red teaming with PyRIT, and the maturity signal that separates a demo from a system: a deployment blocked by a number.
AI FinOps beyond caching: how to choose Batch, Model Router, PTU, and pay-as-you-go
Prompt caching solves reuse, but it does not decide when to run, how to buy capacity, or which model should answer. A practical framework for combining Batch, PTU, pay-as-you-go, and Model Router around cost per approved task.
Data ontology: the governed context that makes AI reason across Databricks and Fabric
The bottleneck of enterprise AI is not the model, it is governed business context. How Unity Catalog Metric Views, Genie Ontology and Fabric IQ form a single semantic layer over one copy of the data — with an FSI use case, cost model and roadmap.