Microsoft Cloud Library

Cohere Parse, a vision language model built for converting enterprise documents into structured, machine-readable data, is now available in the Microsoft Foundry model . Parse joins Cohere’s Embed and Rerank models in Foundry. What Parse does Cohere Parse takes complex, … Continue Reading

The next wave of AI applications won’t be defined by how quickly models answer questions. They’ll be defined by how much work they can complete. Whether resolving repository issues, navigating codebases, generating engineering designs, or executing multi-step enterprise workflows, developers … Continue Reading

Bob Ward and I recently released a series of videos, read more in the original blog post or go directly to the series on YouTube. The Azure SQL Database Foundations series are four videos that take you from your first … Continue Reading

Overview Microsoft HPC Pack is a Windows‑based high‑performance computing (HPC) scheduler that enables customers to deploy, manage, and operate HPC workloads in on‑premises and hybrid environments. Since its original release, HPC Pack has supported a range of Windows‑centric HPC scenarios, … Continue Reading

Building AI agents that can actually do things in your business systems—create records, update opportunities, trigger workflows—typically requires weeks of custom integration work. The Dataverse MCP Server changes that. In this tutorial, you’ll connect a Microsoft Foundry agent to your … Continue Reading

Part 2 of a series. Part 1, Grounding Copilot Studio Agents with Azure AI Search and Foundry IQ, defined five grounding patterns. This article gives you a reproducible way to compare them without mixing latency boundaries, billing units, or quality … Continue Reading

Building an agent shouldn’t require you to reinvent platform capabilities. With Microsoft Foundry, hosted agents inherit essential capabilities such as authentication, ingress management, A2A transport, and discovery endpoints, freeing developers to focus on business logic and user value. This article … Continue Reading

Imagine a customer support agent that answers invoice questions. During testing, everything works perfectly. But in production: The Finance API occasionally times out. The knowledge base contains outdated information. Tool calls fail during peak traffic. Token consumption rises unexpectedly. The … Continue Reading

Open models are driving a new wave of AI innovation, giving organizations more freedom to choose the models that best fit their requirements for performance, cost, latency, customization, and governance. As the open model ecosystem evolves rapidly, developers want access … Continue Reading

Across Microsoft, “hill climbing” has become shorthand for how real AI progress happens: not in one dramatic leap, but through a disciplined loop. Microsoft AI defines the hill climb as an organization that continuously improves, cycle after cycle, through more compute, better … Continue Reading

Use ACS to enforce Scope, Anchored Decisions, Flow Integrity, and Escalation while the agent runs, then prove the controls without model variance. A help desk agent receives two reports that sound almost identical: “I cannot sign in.” In the first … Continue Reading

If you’ve been building local prototypes, internal tools, web backends, or lightweight services on SQL Server Express, you know the routine: it’s free, familiar, and gets the job done – until you hit hardware limits or spend weekends manual backup … Continue Reading

Writing and maintaining SQL is easier when you can eliminate repetitive steps and keep your scripts cleanly formatted. With the MSSQL extension for VS Code v1.45, we’re introducing the Public Preview of the SQL Formatter alongside the General Availability of … Continue Reading

The AI agent has moved from pilot project to production faster than most security programs were built to handle. Every AI agent you deploy is now a security problem before it is a productivity win. This Microsoft Agent 365 security … Continue Reading

… Continue Reading

Hybrid search is usually described as combining keyword search with vector search. Microsoft SQL does that, for sure, but we do quite a bit more right out of the box. SQL dynamically evaluates queries and switches between kNN and ANN … Continue Reading

Why production AI retrieval depends on more than vector index performance. It’s easy to think of AI retrieval as a vector search problem. For many developers, the first conversation starts with vector index benchmarks: How many queries per second can … Continue Reading

… Continue Reading

GPT-chat-latest in Microsoft Foundry is built on GPT-5.6 Sol, bringing focused responses, improved factual reliability, and consistent behavior to conversational applications without requiring developers to select a newly named model endpoint. This update gives developers access to the latest chat … Continue Reading

Let’s start with an admission: developers all hate BlockOnPossibleDataLoss. It is the bane of a smooth development workflow, as significant schema changes can block deployment because of BlockOnPossibleDataLoss. Having said that, there’s more to life than the developer’s local loop … Continue Reading

A user asks an AI agent a simple question: “Create a procurement request for 10 laptops for the new project team.” The agent does what it was designed to do. It checks the procurement policy. It verifies budget availability. It … Continue Reading

… Continue Reading

Workflow automation scenarios—including grounding AI agents, verifying identities, assisting customers with documents in call centers, and triggering document-based workflows—depend on immediate content processing, where every second matters. Now in public preview, synchronous Read, Layout, and Digital Parse operations in Azure … Continue Reading

… Continue Reading

**Disclaimer:** This is an independent, self-built project and is not an official Microsoft tool or service. It reads public security-update data and is intended as an educational example of building an MCP server, hosting it responsibly on Azure, and evaluating … Continue Reading

… Continue Reading

As app developers, our primary focus is building great user experiences, designing APIs, and shipping features quickly. What we don’t want is database friction—wasting hours configuring local DB instances, writing verbose migration scripts by hand, or worrying about unexpected cloud … Continue Reading

Authors: Abi Komma, Charles Kim, Luffy Chen, Morteza Ziyadi Why hand-tuning agents does not scale  An agent’s behavior comes mostly from its natural-language configuration: its instructions, skills, and tool descriptions. Most teams tune that configuration by hand. You write the instruction, … Continue Reading

The setup You’ve built the deployment the enterprise architecture review asked for. Nothing touches the public internet. Your Microsoft Foundry resource is private — public network access disabled, a private endpoint fronting it inside your virtual network. Every resource the … Continue Reading

Microsoft Foundry is no longer just a shelf of foundation models. It is becoming an enterprise model portfolio: frontier models for complex reasoning, cost-optimized models for scale, specialized models for documents and media, and first-party Microsoft AI models for text, … Continue Reading