Kategorie: Microsoft Azure

Microsoft Azure delivers the first large scale cluster with NVIDIA GB300 NVL72 for OpenAI workloads

Microsoft delivers the first at-scale production cluster with more than 4,600 NVIDIA GB300 NVL72, featuring NVIDIA Blackwell Ultra GPUs connected through the next-generation NVIDIA InfiniBand network. This cluster is the first of many, as we scale to hundreds of thousands of Blackwell Ultra GPUs deployed across Microsoft’s AI datacenters globally, reflecting our continued commitment to redefining AI infrastructure and collaboration with NVIDIA. The massive scale clusters with Blackwell Ultra GPUs will enable model training in weeks instead of months, delivering high throughput for inference workloads. We are also unlocking bigger, more powerful models, and will be the first to support training models with hundreds of trillions of parameters.

This was made possible through collaboration across hardware, systems, supply chain, facilities, and multiple other disciplines, as well as with NVIDIA.

Power groundbreaking AI innovation with Azure AI Infrastructure

Microsoft Azure’s launch of the NVIDIA GB300 NVL72 supercluster is an exciting step in the advancement of frontier AI. This co-engineered system delivers the world’s first at-scale GB300 production cluster, providing the supercomputing engine needed for OpenAI to serve multitrillion-parameter models. This sets the definitive new standard for accelerated computing.
Ian Buck, Vice President of Hyperscale and High-performance Computing at NVIDIA

From NVIDIA GB200 to GB300: A new standard in AI performance

Earlier this year, Azure introduced ND GB200 v6 virtual machines (VMs), accelerated by NVIDIA’s Blackwell architecture. These quickly became the backbone of some of the most demanding AI workloads in the industry, including for organizations like OpenAI and Microsoft who already use massive clusters of GB200 NVL2 on Azure to train and deploy frontier models.

Now, with ND GB300 v6 VMs, Azure is raising the bar again. These VMs are optimized for reasoning models, agentic AI systems, and multimodal generative AI. Built on a rack-scale system, each rack has 18 VMs with a total of 72 GPUs:

72 NVIDIA Blackwell Ultra GPUs (with 36 NVIDIA Grace CPUs).

800 gigabits per second (Gbp/s) per GPU cross-rack scale-out bandwidth via next-generation NVIDIA Quantum-X800 InfiniBand (2x GB200 NVL72).

130 terabytes (TB) per second of NVIDIA NVLink bandwidth within rack.

37TB of fast memory.

Up to 1,440 petaflops (PFLOPS) of FP4 Tensor Core performance.

Building for AI supercomputing at scale

Building infrastructure for frontier AI requires us to reimagine every layer of the stack—computing, memory, networking, datacenters, cooling, and power—as a unified system. The ND GB300 v6 VMs are a clear representation of this transformation, from years of collaboration across silicon, systems, and software.

At the rack level, NVLink and NVSwitch reduce memory and bandwidth constraints, enabling up to 130TB per second of intra-rack data-transfer connecting 37TB total of fast memory. Each rack becomes a tightly coupled unit, delivering higher inference throughput at reduced latencies on larger models and longer context windows, empowering agentic and multimodal AI systems to be more responsive and scalable than ever.

To scale beyond the rack, Azure deploys a full fat-tree, non-blocking architecture using NVIDIA Quantum-X800 Gbp/s InfiniBand, the fastest networking fabric available today. This ensures that customers can scale up training of ultra-large models efficiently to tens of thousands of GPUs with minimal communication overhead, thus delivering better end-to-end training throughput. Reduced synchronization overhead also translates to maximum utilization of GPUs, which helps researchers iterate faster and at lower costs despite the compute-hungry nature of AI training workloads. Azure’s co-engineered stack, including custom protocols, collective libraries, and in-network computing, ensures the network is highly reliable and fully utilized by the applications. Features like NVIDIA SHARP accelerate collective operations and double effective bandwidth by performing math in the switch, making large-scale training and inference more efficient and reliable.

Azure’s advanced cooling systems use standalone heat exchanger units and facility cooling to minimize water usage while maintaining thermal stability for dense, high-performance clusters like GB300 NVL72. We also continue to develop and deploy new power distribution models capable of supporting the high energy density and dynamic load balancing required by the ND GB300 v6 VM class of GPU clusters.

Further, our reengineered software stacks for storage, orchestration, and scheduling are optimized to fully use computing, networking, storage, and datacenter infrastructure at supercomputing scale, delivering unprecedented levels of performance at high efficiency to our customers.

Looking ahead

Microsoft has invested in AI infrastructure for years, to allow for fast enablement and transition into the newest technology. It is also why Azure is uniquely positioned to deliver GB300 NVL72 infrastructure at production scale at a rapid pace, to meet the demands of frontier AI today.

As Azure continues to ramp up GB300 worldwide deployments, customers can expect to train and deploy new models in a fraction of the time compared to previous generations. The ND GB300 v6 VMs v6 are poised to become the new standard for AI infrastructure, and Azure is proud to lead the way, supporting customers to advance frontier AI development.

Stay tuned for more updates and performance benchmarks as Azure expands production deployment of NVIDIA GB300 NVL72 globally.

Read more from NVIDIA here.
The post Microsoft Azure delivers the first large scale cluster with NVIDIA GB300 NVL72 for OpenAI workloads appeared first on Microsoft Azure Blog.
Quelle: Azure

Unleash your creativity at scale: Azure AI Foundry’s multimodal revolution

Imagine a platform where every developer—whether you’re building for a startup or a global enterprise—can unlock the full spectrum of AI: text, images, audio, and video. This OpenAI DevDay, Azure AI Foundry is making that vision real. With today’s launch of OpenAI GPT-image-1-mini, GPT-realtime-mini, and GPT-audio-mini, plus major safety upgrades to GPT-5, you now have the ultimate toolkit to create, experiment, and scale multimodal solutions—faster and more affordably than ever before. We are excited to share that the models announced today by OpenAI will be rolling out now in Azure AI Foundry, with most customers being able to get started on October 7, 2025.

Try Azure AI Foundry today

Today’s announcement joins major innovations we announced last week with the launch of the Microsoft Agent Framework (now in preview), multi-agent workflows in Foundry Agent Service in private preview, unified observability, Voice Live API general availability, and the new Responsible AI capabilities. Microsoft Agent Framework (GitHub) is a commercial-grade, open-source SDK, and runtime designed to simplify the orchestration of multi-agent systems. It unifies the business-ready foundations of Semantic Kernel with the multi-agent capabilities of AutoGen, giving developers the tools to build intelligent, scalable agentic solutions with speed and confidence.

By expanding Azure AI Foundry with the latest OpenAI models and advancing our agentic AI framework, we empower customers with unparalleled choice, flexibility, and business capabilities, enabling developers to build intelligent agent systems that address complex business needs and drive innovation at scale.

Meet the new models: Built for developers, ready for anything

GPT-image-1-mini: Compact power for visual creativity

GPT-image-1-mini is purpose-built for organizations and developers who need rapid, resource-efficient image generation at scale. Its compact architecture enables high-quality text-to-image and image-to-image creation while consuming fewer computational resources, allowing teams to deploy multimodal AI even in constrained settings. Its robust architecture built on Image-1 model optimizes consistency and ease of adoption for organizations already leveraging multimodal AI in Azure AI Foundry.

What makes it special?

Flexible image generation: Deploy high-quality text-to-image and image-to-image features without breaking your budget.

Lightning-fast inference: Generate images in real time, seamlessly integrated with existing Azure AI Foundry workflows.

Use cases:

Generating educational materials for classrooms and online learning.

Designing storybooks and visual narratives.

Producing game assets for rapid prototyping and development.

Accelerating UI design workflows for apps and websites.

Table 1: GPT-image-1-mini pricing and deployment in Azure AI Foundry (per 1m tokens)*

GPT-realtime-mini and GPT-audio-mini: Efficient and affordable voice solution

The two new mini models are designed for organizations and developers who need fast, cost-effective multimodal AI without sacrificing quality. These models are lightweight and highly optimized, delivering real-time voice interaction and audio generation with minimal resource requirements. Their streamlined architecture enables rapid inference and low latency, making them ideal for scenarios where speed and responsiveness are critical—such as voice-based chatbots, real-time translation, and dynamic audio content creation. By consuming fewer computational resources, these models help businesses and developer teams reduce operational costs while scaling multimodal capabilities across a wide range of applications.

What makes them special?

Real-time responsiveness: Power chatbots, assistants, and translation tools with near-zero latency.

Resource-light: Run advanced voice and audio models on minimal infrastructure.

Affordable scaling: Lower your operational costs while expanding multimodal capabilities.

Use cases:

Voice-based chatbots for customer service and support.

Real-time translation for global communication.

Dynamic audio content creation for media and entertainment.

Interactive voice assistants for enterprise and consumer applications.

GPT‑realtime‑mini in Azure AI Foundry enables our customer to build voice solutions with lower latency, better instruction adherence, and cost efficiency—capabilities our customers value, driving shorter handle times, smoother dialogues, and faster time‑to‑value.
Andy O’Dower, VP of Product, Twilio

Table 2: GPT-realtime-mini and GPT-audio-mini pricing and deployment in Azure AI Foundry (per 1m tokens)*

GPT-5-chat-latest: Raising the bar for safety and wellbeing

The latest GPT-5-chat-latest update in Azure AI Foundry introduces a more robust set of safety guardrails, designed to better protect users during sensitive conversations. With enhanced detection and response capabilities, GPT-5-chat-latest is now equipped to more effectively recognize and manage dialogue that could lead to mental or emotional distress. These improvements reflect our ongoing commitment to responsible AI, ensuring that every interaction is not only intelligent and helpful, but also safe and supportive for users in challenging moments.

Table 3: GPT-5-chat-latest pricing and deployment in Azure AI Foundry (per 1m tokens)*

GPT-5-pro: The pinnacle of reasoning and analytics

GPT-5-pro represents the pinnacle of advanced reasoning and analytics within the Azure AI Foundry ecosystem, delivering research-grade intelligence. When deployed through Foundry, GPT-5-pro’s tournament-style architecture leverages multiple reasoning pathways to ensure maximum accuracy and reliability, making it ideal for complex analytics, code generation, and decision-making workflows. With Azure AI Foundry, organizations unlock the full potential of GPT-5-pro, driving smarter decisions and accelerating innovation across their most critical business processes, securely and reliably.

Table 4: GPT-5-pro pricing and deployment in Azure AI Foundry (per 1m tokens)*

The developer’s edge: Build, experiment, and ship—faster

With these new models, Azure AI Foundry isn’t just keeping up—it’s setting the pace. Developers can now move beyond text, tapping into image and audio generation, editing, and understanding. The result? Richer, smarter workflows that drive innovation in every industry—from education and gaming to enterprise automation.

Sneak peek: Sora 2—Next-level video and audio generation

And there’s more on the horizon. Sora 2 in Azure AI Foundry is coming soon, bringing advanced video and audio generation in a single API. Imagine physics-driven animation, synchronized dialogue, and cameo features—all available to developers through Azure AI Foundry. Stay tuned for the next wave of immersive, generative experiences.

Are you ready to create the next wave of immersive, multimodal experiences? Azure AI Foundry is your platform for every possibility.

*Pricing is accurate as of October 2025.
The post Unleash your creativity at scale: Azure AI Foundry’s multimodal revolution appeared first on Microsoft Azure Blog.
Quelle: Azure

Introducing Microsoft Agent Framework

Today we’re announcing new capabilities in Azure AI Foundry that make it easier for developers to build, observe, and govern multi-agent systems, while helping organizations close the trust gap in AI.

As agentic AI adoption accelerates—eight in ten enterprises now use some form of agent-based AI, according to PwC1—the complexity of managing these systems is increasing. Developers face fragmented tooling, and organizations struggle to ensure agents behave responsibly. Our latest updates to Azure AI Foundry address these challenges head-on. 

Introducing Microsoft Agent Framework (public preview) 

The Microsoft Agent Framework, now in public preview, is the open-source SDK and runtime that simplifies the orchestration of multi-agent systems. It converges AutoGen, a former Microsoft Research project, and the enterprise-ready foundations of Semantic Kernel into a unified, commercial-grade framework—bringing cutting-edge research to developers.

Get started with the Microsoft Agent Framework

With Microsoft Agent Framework, developers can: 

Experiment locally and then deploy to Azure AI Foundry with observability, durability, and compliance built in. 

Integrate any API via OpenAPI, collaborate across runtimes with Agent2Agent (A2A), and connect to tools dynamically using Model Context Protocol (MCP). 

Use the latest multi-agent patterns like Magentic One and orchestrate agents into Workflows. 

Reduce context-switching across tools and platforms. 

Build multi-agent systems connecting Azure AI Foundry, Microsoft 365 Copilot, and other agent platforms.

This framework is designed to help developers stay in flow. According to an industry study2, 50% of developers lose more than 10 hours per week due to inefficiencies like fragmented tools, highlighting the need for solutions that reduce complexity and improve the developer experience.

One organization using Microsoft Agent Framework to reduce friction is KPMG. KPMG’s transformation began with KPMG Clara, its cloud-based smart audit platform used on every KPMG audit worldwide.

KPMG Clara AI is tightly aligned with the next-generation, open-source Microsoft Agent Framework, built on the convergence of Semantic Kernel and AutoGen.

This means KPMG Clara AI can connect specialized agents to enterprise data and tools, while benefiting from built-in safeguards and an open, extensible developer ecosystem. The framework’s open-source connectors allow agents in KPMG Clara AI to interoperate not only with Azure AI Foundry, but also with external systems and language models, making it possible to scale multi-agent collaboration across a global, regulated enterprise.

Foundry Agent Service and Microsoft Agent Framework connect our agents to data and each other, and the governance and observability in Azure AI Foundry provide what KPMG firms need to be successful in a regulated industry.
— Sebastian Stöckle, Global Head of Audit Innovation and AI at KPMG International

We invite developers to join us in shaping the future of agentic AI by contributing code and feedback to Microsoft Agent Framework. 

Multi-agent workflows (private preview) 

Building on Microsoft Agent Framework, we’re extending these capabilities directly into the cloud with multi-agent workflows in Foundry Agent Service. This new feature enables developers to orchestrate sophisticated, multi-step business processes using a structured, stateful workflow layer. 

With multi-agent workflows, teams can: 

Coordinate multiple agents across long-running tasks with persistent state and context sharing. 

Automate complex enterprise scenarios such as customer onboarding, financial transaction processing, and supply chain automation. 

Leverage built-in error handling, retries, and recovery to improve reliability at scale. 

Workflows can be authored and debugged visually through the VS Code Extension or Azure AI Foundry, then deployed, tested, and managed in Foundry alongside existing solutions. 

Several customers are currently experimenting with this capability, and we look forward to expanding to more customers in the coming weeks.

Multi-agent observability across popular frameworks with OpenTelemetry contributions 

We’re also announcing enhancements to multi-agent observability, with contributions to OpenTelemetry that help standardize tracing and telemetry for agentic systems.

This gives teams deeper visibility into agent workflows, tool call invocations, and collaboration—critical for debugging, optimization, and compliance. We made the above enhancements to OpenTelemetry in collaboration with Outshift, Cisco’s incubation engine. 

With the above enhancements, Azure AI Foundry now provides unified observability for agents built with multiple frameworks, including Microsoft Agent Framework and others like LangChain, LangGraph, and OpenAI Agents SDK.

Voice Live API in Azure AI Foundry now generally available 

Mutli-agent workflows are increasingly initiated through voice inputs and culminate in voice outputs. We’re excited to announce the general availability of Voice Live API, which empowers developers and enterprises to build scalable, production-ready voice AI agents. Voice Live API is a unified, real-time speech-to-speech interface that integrates speech-to-text (STT), generative AI models, text-to-speech (TTS), avatar, and conversational enhancement features into a single, low-latency pipeline. 

Organizations such as Capgemini, healow, Astra Tech, and Agora are leveraging Voice Live API to build customer service agents, educational tutors, HR assistants, and multilingual agents. Voice Live API is transforming how developers build voice AI agents by providing an integrated, scalable, and efficient solution. 

Responsible AI capabilities public preview 

Building on advancements in agent observability and framework integration, it’s equally important to ensure that AI systems operate responsibly and securely—especially as they become more deeply embedded in critical enterprise workflows. 

According to McKinsey’s 2025 Global AI Trust Survey3, the number one barrier to AI adoption is lack of governance and risk-management tools. That’s why we’re putting the following responsible AI features in public preview in the coming weeks:

Task adherence: Help agents stay aligned with assigned tasks. 

Prompt shields with spotlighting: Protect against prompt injection and spotlight risky behavior. 

PII detection: Identify and manage sensitive data. 

These capabilities are built into Azure AI Foundry, helping organizations build with confidence and comply with internal and external standards. 

Customer momentum 

Azure AI Foundry solutions are helping over 70,000 organizations worldwide—from digital natives to enterprise companies—transform AI innovation into practical results. For example: 

Commerzbank: Commerzbank is piloting Microsoft Agent Framework to power avatar-driven customer support, enabling more natural, accessible, and compliant customer interactions.

The new Microsoft Agent Framework simplifies coding, reduces efforts and fully supports MCP for agentic solutions. We are really looking forward to the productive usage of container-based Azure AI Foundry agents, which significantly reduces workload in IT operations.
— Gerald Ertl, Managing Director/Head of Digital Banking Solutions, Commerzbank AG

Citrix: Citrix is exploring how they can use agentic AI within virtual desktop infrastructure (VDI) environments to improve enterprise productivity and efficiency.

Citrix has always embraced flexible ways of working as the leader in secure work. As we move into a world where agentic AI works side-by-side with us, we’re excited to enable that also within workspaces that our customers already use every day. Microsoft’s Agent Framework brings a modern, developer-first approach to building agents. With support for key APIs and languages, and native adoption of emerging protocols for tool calling and observability, it enables intuitive development of agents on Azure AI Foundry without compromising developer control. We are eager to leverage the framework to deliver on our vision – enterprise-scale, production-ready AI agents for our customers.
— George Tsolis, Distinguished Engineer, Citrix

TCS: Tata Consultancy Services is actively building a multi-agent practice on the Microsoft Agent Framework, with several initiatives underway that showcase their strategic investment and technical depth, including agentic solutions for finance, IT operations, and retail.

Adopting Microsoft Agent Framework is not just a technological advancement, but a bold step towards reimagining industry value chains. By harnessing Agentic AI and Frontier models, we enable our teams to build flexible, scalable, enterprise-grade solutions that transform workflows and deliver value across platforms. True leadership is about empowering innovation, embracing change, and fostering an environment where agility and collaboration drive excellence. 
— Girish Phadke, Head, Microsoft Azure Practice, TCS

Sitecore: Sitecore is developing a solution that enables marketers to interact seamlessly with the platform by automating tasks across the entire content supply chain—from creating and managing web experiences to handling digital assets—using intelligent agents.

By partnering with Microsoft to leverage its new Microsoft Agent Framework, Sitecore can bring together the best of both worlds: the flexibility to power fully non-deterministic agentic orchestrations and the reliability to run more deterministic, repeatable agents. At the same time, we benefit from Microsoft’s enterprise-grade observability and telemetry, ensuring that these orchestrations are not only powerful but also secure, measurable, and production-ready.
— Mo Cherif, VP of AI, Sitecore

Elastic: Elasticsearch supports a native connector to Microsoft Agent Framework, enabling developers to seamlessly integrate enterprise data into intelligent agents and workflows.

Elasticsearch is the context engineering platform and vector database of choice for organizations to store and search their most valuable operational and business data. With the new Microsoft Agent Framework connector, developers can now bring the most relevant organizational context directly into intelligent agents and multi-agent workflows. This makes it easier than ever to build production-ready AI solutions that combine the reasoning power of agents with the speed and scale of Elasticsearch.
— Steve Kearns, General Manager Search Solutions, Elastic

A trusted agent factory for developers 

Azure AI Foundry is more than a platform—it’s a trusted agent factory for developers and enterprises. Whether you’re a CIO looking to scale AI responsibly, a security architect focused on governance, or a developer building the next generation of intelligent agents, Azure AI Foundry provides the tools, frameworks, and trust you need. 

Microsoft stands out in the AI landscape with its commitment to open standards, interoperability, and responsible AI. The Microsoft Agent Framework, now in public preview, is a unified, enterprise-grade framework that integrates cutting-edge research and allows developers to seamlessly orchestrate multi-agent systems with built-in observability, durability, and compliance.

Unlike other solutions, our framework supports integration with any API via OpenAPI, collaboration across runtimes with Agent2Agent (A2A), and dynamic tool connections using MCP. This ensures developers can reduce context-switching and stay in flow, accelerating innovation.

The open-source nature of the framework invites developers to contribute and shape the future of agentic AI, making it a truly collaborative and forward-thinking platform. With Microsoft, organizations can trust that their AI systems will be powerful, efficient, responsible, and secure, addressing the top barriers to AI adoption identified in McKinsey’s 2025 Global AI Trust Survey.

Learn more about Azure AI Foundry

1 PwC’s AI Agent Survey.

2 AI adoption is rising, but friction persists.

3 Insights on responsible AI from the Global AI Trust Maturity Survey.
The post Introducing Microsoft Agent Framework appeared first on Microsoft Azure Blog.
Quelle: Azure

Grok 4 is now available in Azure AI Foundry: Unlock frontier intelligence and business-ready capabilities

Today’s enterprises are entering a new phase of AI adoption—one where trust, flexibility, and production readiness aren’t optional; they’re foundational. Microsoft has collaborated closely with xAI to bring Grok 4, their most advanced model, to Azure AI Foundry—delivering powerful reasoning within a platform designed for business-ready safety and control.

Check out the Azure AI Foundry Grok 4 model card

Grok 4 undeniably has exceptional performance. With a 128K-token context window, native tool use, and integrated web search, it pushes the boundaries of what’s possible in contextual reasoning and dynamic response generation. But performance alone isn’t enough. AI at the frontier must also be accountable. Over the last month, xAI and Microsoft have worked closely to enhance responsible design. The team has evaluated from a responsible AI perspective, putting Grok 4 through a suite of safety tests and compliance checks. Azure AI Content Safety is on by default, adding another layer of protection for enterprise use. Please see the Foundry model card for more information about model safety.

In this blog, we’ll explore what makes Grok 4 stand out, how it compares to other frontier models, and how developers can access it via Azure AI Foundry.

Grok 4: Enhanced reasoning, expanded context, and real-time insights

Grok models were trained on xAI’s Colossus supercomputer, utilizing a massive compute infrastructure that xAI claims delivers a 10 times leap in training scale compared to Grok 3. Grok 4’s architecture marks a significant shift from its predecessors, emphasizing reinforcement learning (RL) and multi-agent systems. According to xAI, the model prioritizes reasoning over traditional pre-training, with a heavy focus on RL to refine its problem-solving capabilities.

Key architectural highlights include:

First-principles reasoning: “think mode”

One of Grok 4’s headline features is its first-principles reasoning ability. Essentially, the model tries to “think” like a scientist or detective, breaking problems down step by step. Instead of just blurting out an answer, Grok 4 can work through the logic internally and refine its response. It has strong proficiency in math (solving competition-level problems), science, and humanities questions. Early users have noted it excels at logic puzzles and nuanced reasoning better than some incumbent models, often finding correct answers where others get confused. Put simply, Grok 4 doesn’t just recall information—it actively reasons through problems. This focus on logical consistency makes it especially attractive if your use case requires step-by-step answers (think of research analysis, tutoring, or complex troubleshooting scenarios).

Example prompt: Explain how you would generate electricity on Mars if you had no existing infrastructure. Start from first principles: what are the fundamental resources, constraints, and physical laws you would use?

Extended context window

Perhaps one of Grok 4’s most impressive technical feats is its handling of extremely large contexts. The model is built to process and remember massive amounts of text in one go. In practical terms, this means Grok 4 can ingest extensive documents, lengthy research papers, or even a large codebase, and then reason about them without needing to truncate or forget earlier parts. For use cases like:

Document analysis: You could feed in hundreds of pages of a document and ask Grok to summarize, find inconsistencies, or answer specific questions. Grok 4 is far less likely to miss the details simply because it ran out of context window, compared to other models.

Research and academia: Load an entire academic journal issue or a very long historical text and have Grok analyze it or answer questions across the whole text. It could, for example, take in all of Shakespeare’s plays and answer a question that requires connecting info from multiple plays.

Code repositories: Developers could input an entire code repository or multiple files (up to millions of characters of code) and ask Grok 4 to find where a certain function is defined, or to detect bugs across the codebase. This is huge for understanding large legacy projects.

xAI has claimed that this is not just “memory” but “smart memory.” Grok can intelligently compress or prioritize information in very long inputs, remembering the crucial pieces more strongly. For the end user or developer, the takeaway is: Grok 4 can handle very large input texts in one shot. This reduces the need to chop up documents or code and manage context fragments manually. You can throw a ton of information at it and it can keep the whole thing “in mind” as it responds.

Example prompt: Read this Shakespeare play and find my password (password is buried in the long context text).

Data-aware responses and real-time insights

Another strength of Grok 4 is how it can integrate external data sources and trending information into its answers—effectively acting as a data analyst or real-time researcher when needed. It understands that sometimes the best answer needs to come from outside its training data, and it has mechanisms to retrieve and incorporate that external data. It turns the chatbot into more of an autonomous research assistant. You ask a question, it might go read a few things online, and come back with an answer that’s enriched by real data. Of course, caution is needed—live data can sometimes be incorrect, or the model might pick up on biased sources; one should verify critical outputs.

Example prompt: Check the latest news on global AI regulations (past 48 hours). 

Summarize the top 3 developments.

Highlight which regions or governments are driving the changes.

Explain what impact these updates could have on companies deploying foundation models.

Provide the sources you referenced.

Stacking up Grok 4: How it performs against top models

Grok 4 showcases impressive capabilities on high-complexity tasks. These benchmarks underscore Grok 4’s leading-edge capabilities in high-level reasoning, STEM disciplines, complex problem-solving, and industry-specific tasks. These benchmark numbers are calculated using our own internal Azure AI Foundry benchmarking service, which we use to compare models across a set of industry standard benchmarks.

Family of Grok models 

 In addition to Grok 4, Azure AI Foundry also has 3 additional Grok models already available.

Grok 4 Fast Reasoning is optimized for tasks requiring logical inference, problem-solving, and complex decision-making, making it ideal for analytical applications.

Grok 4 Fast Non-Reasoning focuses on speed and efficiency for straightforward tasks like summarization or classification, without deep logical processing.

Grok Code Fast 1 is tailored specifically for code generation and debugging, excelling in programming-related tasks across multiple languages.

While all three models prioritize speed, their core strengths differ: reasoning for logic-heavy tasks, non-reasoning for lightweight operations, and code for developer workflows. 

Pricing including Azure AI Content Safety: 

Model Deployment Type Price $/1M tokens Grok 4 Global Standard Input- $5.5 Output- $27.5 

Get started with Grok 4 in Azure AI Foundry

Lead with insight, build with trust. Grok 4 unlocks frontier‑level reasoning and real‑time intelligence, but it is not a deploy and forget model. Pair Azure’s guardrails with your own domain checks, monitor outputs against evolving standards, and iterate responsibly—while we continue to harden the model and disclose new safety scores. Please see the Azure AI Foundry Grok 4 model card for more information about model safety.

Head over to ai.azure.com, search for “Grok,” and start exploring what these powerful models can do.

Azure AI Foundry
Explore the Grok 4 model in Azure AI Foundry.

Try it now

The post Grok 4 is now available in Azure AI Foundry: Unlock frontier intelligence and business-ready capabilities appeared first on Microsoft Azure Blog.
Quelle: Azure

Agent Factory: Designing the open agentic web stack

This blog is a wrap-up post in a blog series called Agent Factory which shares best practices, design patterns, and tools to help guide you through adopting and building agentic AI.

The rise of AI agents—autonomous software entities acting on behalf of users and organizations—marks a transformative moment for enterprise technology. But as we’ve explored throughout this blog series, building effective agents is about more than just code. It requires a repeatable blueprint, spanning use case design, developer tooling, observability, integrations, and governance. 

Throughout this series, we’ve walked through the journey of building enterprise-grade agents: from early use cases and design patterns to the tools and developer workflows needed to move from prototype to production, to the importance of observability, interoperability, and open standards, and finally the governance and security principles required to deploy agents responsibly. 

Now, as we conclude the series, we zoom out to the bigger picture: the agentic web stack. Much like HTTP and TCP/IP standardized the internet, this stack provides the common services and protocols needed to make multi-agent ecosystems secure, scalable, and interoperable across organizational boundaries. 

Learn more with Azure AI Foundry

Blueprint: 8 essential components and services

A robust agentic web stack is not one technology but a composition of services that together provide the foundation for open, secure, and enterprise-grade multi-agent systems. Here’s what it takes—and how Azure AI Foundry is making it real. 

1. Communication protocol service

Agents need a shared “language” to exchange messages, requests, and structured data. Without it, collaboration breaks down into isolated silos. Standards like Model Context Protocol (MCP) and Agent-to-Agent (A2A) provide this foundation, ensuring agents can negotiate, coordinate, and cooperate—regardless of who built them or where they’re hosted. In Azure AI Foundry, A2A support enables not only intra-organization workflows but also cross-boundary collaboration, where supply chain partners or business ecosystems can securely exchange actions through a common protocol.

2. Discovery registry service

Just as the web needed directories and search engines, agents need a way to be found and reused. The Catalog serves as the listing of assets—a curated collection of agents, tools, and applications that can be discovered and composed into new solutions. The Registry, by contrast, tracks the deployed instances of those assets—the live agentic app instances running across providers, with their endpoints, health, and status. Together, the Catalog and Registry bridge the gap between what’s available and what’s active, enabling developers to publish once, discover broadly, and reliably orchestrate workflows against running systems.

3. Identity and trust management service

Trust is the lifeblood of the agentic web. Every agent must carry a verifiable identity, enforced through standards like OIDC (OpenID Connect) and JWT (JSON Web Token), and tied into enterprise systems like Microsoft Entra ID. In Azure AI Foundry, identity is not an afterthought—it’s the control plane. This enables fine-grained role-based access, ensures that only authorized actors participate in workflows, and provides auditable accountability for every action an agent takes. Combined with encrypted channels, this identity-first model enforces a zero-trust security posture across the agentic stack.

4. Tool invocation and integration service

No agent can succeed in isolation; value comes when agents can connect with data, APIs, and enterprise systems. The Model Context Protocol (MCP) provides a vendor-neutral standard for exposing tools in a way that any compliant agent can invoke. In Azure AI Foundry, MCP integration is deeply embedded, so developers can register enterprise APIs once and instantly make them available to multiple agents—whether they’re built on Microsoft’s agent frameworks like Semantic Kernel and AutoGen, LangGraph, or third-party SDKs. This eliminates bespoke integrations and allows enterprises to compose workflows from best-in-class components.

5. Orchestration service

Single agents can handle discrete tasks, but the real breakthroughs come from multi-agent orchestration: teams of agents collaborating across multi-step, distributed processes. Azure AI Foundry delivers this through a unified framework that brings together Semantic Kernel and AutoGen—and extends it with multi-agent workflow orchestration inside Azure AI Foundry Agent Service. These workflows manage dependencies, allocate resources, and resolve conflicts, enabling enterprise-scale use cases such as financial transaction processing or IT incident response.

6. Telemetry and observability service

As we covered in Part 3, observability is non-negotiable for reliable agents. Azure AI Foundry extends OpenTelemetry with agent-aware instrumentation—tracing conversations, capturing performance data, and surfacing anomalies in real time. This makes agent behavior explainable and debuggable, while also serving governance needs: every decision and action is logged, auditable, and tied back to identity. For enterprises, this is the bedrock of trust, compliance, and continuous improvement.

7. Memory service

Agents without memory are limited to stateless interactions; agents with memory become adaptive, contextual, and human-like in their continuity. Azure AI Foundry supports both short-term session memory and long-term enterprise knowledge integration. Imagine a customer support agent that recalls prior interactions across channels, or a supply chain agent that tracks historical disruptions to improve future decisions. With memory, agents evolve from transactional helpers into strategic partners that learn and adapt over time.

8. Evaluation and governance service

Finally, no stack is complete without governance. This includes continuous evaluation, policy enforcement, ethical safeguards, and regulatory compliance. In Azure AI Foundry, governance hooks are built into orchestration, observability, and identity services—enabling enterprises to block unsafe actions, enforce approvals for sensitive workflows, and generate compliance-ready audit trails. This ensures organizations don’t just innovate fast, but innovate responsibly.

Strategic use cases and business value

The agentic web stack is not theoretical; it unlocks concrete enterprise value.

End-to-end business process automation: Imagine a procure-to-pay workflow where one agent negotiates with suppliers, another verifies compliance, a third triggers payment, and a fourth updates ERP records. With Azure AI Foundry’s orchestration and discovery registry, these agents collaborate seamlessly, cutting manual intervention and cycle times from weeks to hours.

Cross-organization supply chain synchronization: In global supply chains, delays often come from mismatched systems and data. With A2A and discovery services, a logistics agent from one company can securely interoperate with a customs agent from another—both governed by identity and observability. The result: faster border clearance, lower costs, and higher resilience. 

Knowledge worker augmentation: Agents built with Azure AI Foundry can take on repetitive but high-value tasks—scheduling, research, first-draft writing—while humans focus on creativity and judgment. The memory integration ensures continuity: a legal research agent remembers prior cases analyzed, while a marketing agent recalls brand guidelines across campaigns.

Complex IT operations: When outages occur, every second counts. Multi-agent workflows in Azure AI Foundry can detect anomalies, route alerts, execute diagnostics, and propose mitigations across distributed environments. Observability ensures root causes are transparent, while governance enforces that corrective actions comply with policy.

Memory-driven customer journeys: A customer support agent that recalls a prior complaint, a personalization agent that adapts recommendations, a compliance agent that enforces rules—working together, these create adaptive, context-rich interactions. The outcome is not just efficiency but stronger relationships and trust.

Preparing for the agentic era

For organizations, the path forward is as much about strategy and culture as it is about technology: 

Start with open standards: Adopt MCP and A2A from the outset, even in pilots, to avoid future rework and ensure interoperability. 

Invest in foundations: Identity, observability, and memory are not optional; they are the pillars that differentiate ad hoc automations from enterprise-grade systems. 

Operationalize governance: Define policies now and embed them into workflows through Azure AI Foundry’s governance services, so oversight scales with adoption. 

Engage the ecosystem: Participate in open-source and standards communities, influence their direction, and ensure your organization’s voice is heard. 

Prepare your workforce: Train employees not just to use agents, but to collaborate with them, supervise them, and improve them over time. 

Leaders who act on these imperatives will not only adopt agentic AI but shape its trajectory in their industries.

Shaping the future together at Ignite 2025 

The Agent Factory series has laid out the foundations: design patterns, developer tools, observability practices, interoperability standards, and governance principles. The agentic web stack brings these threads together into a cohesive vision: an open, secure, and interoperable ecosystem where agents can scale across organizational boundaries. 

Azure AI Foundry is your platform to make this vision real—unifying frameworks, standards, and enterprise capabilities so organizations can accelerate value while staying in control. 

At Ignite 2025, we’ll showcase the next wave of innovations—from multi-agent orchestration to deeper integrations with enterprise apps, data, and security systems. Join us to see how Azure AI Foundry is not only enabling enterprises to adopt agentic AI but also shaping the agent-driven future of business. 

Did you miss these posts in the series?

The new era of agentic AI—common use cases and design patterns

Building your first AI agent with the tools to deliver real-world outcomes

Top 5 agent observability best practices for reliable AI

From prototype to production—developer tools and rapid agent development

Connecting agents, apps, and data with new open standards like MCP and A2A

Creating a blueprint for safe and secure AI agents

Azure AI Foundry
Build AI agents that automate tasks and enhance user experiences.

Learn more

The post Agent Factory: Designing the open agentic web stack appeared first on Microsoft Azure Blog.
Quelle: Azure

How Azure Cobalt 100 VMs are powering real-world solutions, delivering performance and efficiency results

Azure Cobalt 100 is our in-house, custom-built, Arm-based cloud CPU powering general compute workloads in the cloud. Cobalt 100 systems are designed to deliver high performance, energy efficiency, and cost effectiveness for a wide range of workloads. Cobalt 100 systems have been live for nearly a year and now available in 29 Microsoft datacenter regions globally, delivering meaningful results and benefits to Azure customers across industries.

Get started with Azure Cobalt 100 VMs

Cobalt 100, Microsoft’s in-house CPU for the cloud

Cloud analytics leaders like Databricks and Snowflake are adopting Cobalt 100 VMs to support their data platforms. These companies handle massive volumes of data and rely on scalable infrastructure to deliver real-time insights and machine learning capabilities. The balance of compute power and energy efficiency offered by Cobalt 100 VMs makes it an ideal choice for large-scale data processing.

We continue to see adoption of Cobalt 100 VMs from customers who are achieving real world performance and efficiency gains:

“At OneTrust, we’re constantly optimizing our platform to deliver scalable, high-performance solutions for AI-ready governance. The Azure Cobalt 100 VMs represent a major advancement in cloud infrastructure, and we’ve seen meaningful improvements in throughput and efficiency during our evaluations. Microsoft’s innovation in Arm-based architecture enables us to better serve our global enterprise customers with faster, more cost-effective services.”
— Steve Finch, VP of Architecture & Ops, OneTrust

“At Siemens, we’re committed to pushing the boundaries of silicon verification performance. By adopting Azure Cobalt 100 VMs, we’ve achieved up to a  20% performance boost  in our Questa One DFT simulations – accelerating fault and formal verification cycles across analog, memory, and digital workloads. This leap in efficiency empowers our teams to deliver faster, more reliable results for one of the most complex designs in the industry.” 
– Abhi Kolpekwar, VP & GM, Siemens EDA, Siemens Digital Industries Software

“We conducted extensive benchmarking of the new Cobalt 100 VMs for containerized application workloads running on AKS and observed measurable price-performance gains compared to Azure’s previous-generation Arm-based VM series, with improvements evident across both throughput and cost-efficiency metrics. Following these results, we have migrated 70% of our AKS workloads to Cobalt 100 VMs and are in the process of migrating the remaining 30%.”
— Gopala Krishna Padidadakala, Sr Director of Cloud Engineering, Sprinklr

 “Temenos is proud to set a new industry benchmark for scalable, AI-powered banking on Microsoft Azure, leveraging the breakthrough performance of Cobalt 100 VMs. The combination of Temenos’ cloud-native platform and Azure’s Arm-based Cobalt 100 VMs allowed us to achieve over 40% efficiency improvement compared to the 2024 benchmark exercise, enabling banks to run demanding workloads with greater efficiency and sustainability. This collaboration empowers financial institutions to innovate faster and scale securely, transforming the future of digital banking.”  
— Eugene Khmelevsky, Head of Architecture and Data, Temenos

Microsoft’s own services are also benefiting from the adoption of Cobalt 100 VMs. The deployment of Cobalt 100 VMs for Microsoft’s services demonstrates its ability to support large-scale, mission-critical applications.

Microsoft Teams has achieved up to 45% better performance using these VMs than previously possible. Teams is a latency-sensitive application that serves millions of users worldwide, and the ability to process requests more efficiently has a direct impact on user experience. The media processor capability in Teams—supporting audio/video streaming—runs on Cobalt 100 VMs with lower compute footprint. That translates to resource reduction of up to 35% fewer compute cores needed for the workload. Cobalt 100 VMs unlock exceptional efficiency, empowering teams to achieve more, faster, with fewer resources.

Microsoft Defender for Endpoint (MDE) is a cloud-native security service with hundreds of microservices that perform threat detection, data analysis, and protection at massive scale. We have seen 40% better performance in MDE’s cyber data curator, running on Cobalt 100 VMs. Curator groups high-volume data into partitions in real time for fast, scalable processing. Faster processing and higher throughput translate to better user experiences, including faster threat response in MDE.

These results underscore the value of Microsoft’s approach to architect and develop customized infrastructure; Cobalt 100 is not just a new type of general compute VM, but one of the most optimized compute products in Azure. Whether it’s accelerating product development, scaling analytics platforms, or improving user experiences, customers are finding that the combination of performance, efficiency, and cost-effectiveness makes Cobalt 100 VMs a compelling choice for modern cloud workloads.

Cobalt 100 demonstrates Microsoft’s end-to-end systems strategy in practice. By designing the CPU in-house and optimizing it for Azure’s infrastructure, Microsoft has created a tightly integrated infrastructure that delivers consistent performance across a variety of cloud scenarios. This approach allows for better control over power consumption, thermal management, and workload distribution, resulting in a powerful and efficient cloud environment.

As more organizations look to modernize their infrastructure and adopt cloud-native technologies, the demand for highly performant and energy-efficient compute resources will continue to grow. Azure Cobalt 100 VMs are well-positioned to meet this demand, offering a scalable and sustainable solution for a wide range of applications.

By delivering faster, more efficient computing, Azure Cobalt 100 empowers organizations to push the boundaries of what’s possible with better price performance across industry use cases in their respective fields.

Start your journey on Cobalt 100 VMs – try today! 

Check out the Cobalt 100 panel from Arm and Azure at Microsoft Build 2025.

Learn more about Azure’s breakthrough microfluidics cooling for AI chips.

Learn more about how Azure is scaling networking innovation in hollow core fiber.

Learn more about Microsoft’s global infrastructure.  

The post How Azure Cobalt 100 VMs are powering real-world solutions, delivering performance and efficiency results appeared first on Microsoft Azure Blog.
Quelle: Azure

Agent Factory: Creating a blueprint for safe and secure AI agents

This blog post is the sixth out of a six-part blog series called Agent Factory which shares best practices, design patterns, and tools to help guide you through adopting and building agentic AI.

Trust as the next frontier

Trust is rapidly becoming the defining challenge for enterprise AI. If observability is about seeing, then security is about steering. As agents move from clever prototypes to core business systems, enterprises are asking a harder question: how do we keep agents safe, secure, and under control as they scale?

The answer is not a patchwork of point fixes. It is a blueprint. A layered approach that puts trust first by combining identity, guardrails, evaluations, adversarial testing, data protection, monitoring, and governance.

Learn more about building trust with Azure AI Foundry

Why enterprises need to create their blueprint now

Across industries, we hear the same concerns:

CISOs worry about agent sprawl and unclear ownership.

Security teams need guardrails that connect to their existing workflows.

Developers want safety built in from day one, not added at the end.

These pressures are driving the shift left phenomenon. Security, safety, and governance responsibilities are moving earlier into the developer workflow. Teams cannot wait until deployment to secure agents. They need built-in protections, evaluations, and policy integration from the start.

Data leakage, prompt injection, and regulatory uncertainty remain the top blockers to AI adoption. For enterprises, trust is now a key deciding factor in whether agents move from pilot to production.

What safe and secure agents look like

From enterprise adoption, five qualities stand out:

Unique identity: Every agent is known and tracked across its lifecycle.

Data protection by design: Sensitive information is classified and governed to reduce oversharing.

Built-in controls: Harm and risk filters, threat mitigations, and groundedness checks reduce unsafe outcomes.

Evaluated against threats: Agents are tested with automated safety evaluations and adversarial prompts before deployment and throughout production.

Continuous oversight: Telemetry connects to enterprise security and compliance tools for investigation and response.

These qualities do not guarantee absolute safety, but they are essential for building trustworthy agents that meet enterprise standards. Baking these into our products reflects Microsoft’s approach to trustworthy AI. Protections are layered across the model, system, policy, and user experience levels, continuously improved as agents evolve.

How Azure AI Foundry supports this blueprint

Azure AI Foundry brings together security, safety, and governance capabilities in a layered process enterprises can follow to build trust in their agents.

Entra Agent IDComing soon, every agent created in Foundry will be assigned a unique Entra Agent ID, giving organizations visibility into all active agents across a tenant and helping to reduce shadow agents.

Agent controlsFoundry offers industry first agent controls that are both comprehensive and built in. It is the only AI platform with a cross-prompt injection classifier that scans not just prompt documents but also tool responses, email triggers, and other untrusted sources to flag, block, and neutralize malicious instructions. Foundry also provides controls to prevent misaligned tool calls, high risk actions, and sensitive data loss, along with harm and risk filters, groundedness checks, and protected material detection.

Risk and safety evaluationsEvaluations provide a feedback loop across the lifecycle. Teams can run harm and risk checks, groundedness scoring, and protected material scans both before deployment and in production. The Azure AI Red Teaming Agent and PyRIT toolkit simulate adversarial prompts at scale to probe behavior, surface vulnerabilities, and strengthen resilience before incidents reach production.

Data control with your own resourcesStandard agent setup in Azure AI Foundry Agent Service allows enterprises to bring their own Azure resources. This includes file storage, search, and conversation history storage. With this setup, data processed by Foundry agents remains within the tenant’s boundary under the organization’s own security, compliance, and governance controls.

Network isolationFoundry Agent Service supports private network isolation with custom virtual networks and subnet delegation. This configuration ensures that agents operate within a tightly scoped network boundary and interact securely with sensitive customer data under enterprise terms.

Microsoft PurviewMicrosoft Purview helps extend data security and compliance to AI workloads. Agents in Foundry can honor Purview sensitivity labels and DLP policies, so protections applied to data carry through into agent outputs. Compliance teams can also use Purview Compliance Manager and related tools to assess alignment with frameworks like the EU AI Act and NIST AI RMF, and securely interact with your sensitive customer data under your terms.

Microsoft DefenderFoundry surfaces alerts and recommendations from Microsoft Defender directly in the agent environment, giving developers and administrators visibility into issues such as prompt injection attempts, risky tool calls, or unusual behavior. This same telemetry also streams into Microsoft Defender XDR, where security operations center teams can investigate incidents alongside other enterprise alerts using their established workflows.

Governance collaboratorsFoundry connects with governance collaborators such as Credo AI and Saidot. These integrations allow organizations to map evaluation results to frameworks including the EU AI Act and the NIST AI Risk Management Framework, making it easier to demonstrate responsible AI practices and regulatory alignment.

Blueprint in action

From enterprise adoption, these practices stand out:

Start with identity. Assign Entra Agent IDs to establish visibility and prevent sprawl.

Built-in controls. Use Prompt Shields, harm and risk filters, groundedness checks, and protected material detection.

Continuously evaluate. Run harm and risk checks, groundedness scoring, protected material scans, and adversarial testing with the Red Teaming Agent and PyRIT before deployment and throughout production.

Protect sensitive data. Apply Purview labels and DLP so protections are honored in agent outputs.

Monitor with enterprise tools. Stream telemetry into Defender XDR and use Foundry observability for oversight.

Connect governance to regulation. Use governance collaborators to map evaluation data to frameworks like the EU AI Act and NIST AI RMF.

Proof points from our customers

Enterprises are already creating security blueprints with Azure AI Foundry:

EY uses Azure AI Foundry’s leaderboards and evaluations to compare models by quality, cost, and safety, helping scale solutions with greater confidence.

Accenture is testing the Microsoft AI Red Teaming Agent to simulate adversarial prompts at scale. This allows their teams to validate not just individual responses, but full multi-agent workflows under attack conditions before going live.

Learn more

Create with Azure AI Foundry.

Join us at Microsoft Secure on September 30 to learn about our newest capabilities and how Azure AI Foundry integrates with Microsoft Security to help you build safe and secure agents, with speakers including Vasu Jakkal, Sarah Bird, and Herain Oberoi.

Implement a responsible generative AI solution in Azure AI Foundry.

Did you miss these posts in the Agent Factory series?

The new era of agentic AI—common use cases and design patterns

Building your first AI agent with the tools to deliver real-world outcomes

Top 5 agent observability best practices for reliable AI

From prototype to production—developer tools and rapid agent development

Connecting agents, apps, and data with new open standards like MCP and A2A

Azure AI Foundry
Build trustworthy AI agents that automate tasks, enhance user experiences, and deliver results.

Learn more

The post Agent Factory: Creating a blueprint for safe and secure AI agents appeared first on Microsoft Azure Blog.
Quelle: Azure

Microsoft named a Leader in the 2025 Gartner® Magic Quadrant™ for Global Industrial IoT Platforms 

We’re proud to share that Microsoft has been recognized as a Leader in the 2025 Gartner Magic Quadrant for Global Industrial IoT (IIoT) Platforms. We believe this recognition underscores our commitment to empowering industries with intelligent, secure, and scalable solutions that drive real-world impact. 

As industrial organizations continue to modernize their operations, Azure’s adaptive cloud approach, which includes Azure IoT, Azure Arc, and more, can help manufacturing, energy, and logistics organizations to enhance efficiency, optimize performance, and drive secure innovation at scale.

Accelerate digital transformation with Azure IoT

Recognized in industrial IoT

In today’s data-driven industrial landscape, Internet of Things (IoT) technology already serves as a strategic driver of operational excellence and competitiveness. Connected sensors and edge devices capture machines and process data that can then be integrated with other key enterprise systems such as Manufacturing Execution System (MES), Enterprise Resource Planning (ERP), and analytics in digital twin models to predict failures, optimize asset utilization, and reduce downtime. These capabilities result in business value by helping organizations improve key performance indicators (KPIs) such as quality assurance, energy efficiency, and supply chain traceability.

As the backbone for AI, IoT provides high frequency telemetry and controls the pathways needed for advanced analytics and machine learning. This synergy powers additional industrial use cases like self-dispatching field services, vision-based quality inspection, process optimization, energy load balancing, and intelligent operator assistance. Industrial IoT, especially when deployed with an adaptive cloud approach, can transform AI from isolated pilots into scalable, production-grade capabilities that could boost yield, throughput, and sustainability. These capabilities can help unlock a new type of organization, what we call the Frontier Industrial firm—industrial companies operating at the leading edge of digitalization to pursue superior productivity. 

We continue to help industrial organizations transform by focusing on the key areas our customers prioritize: 

Comprehensive platform for industrial needs: Microsoft’s industrial IoT platform enables a wide variety of industrial use cases through its ability to bring data from distributed and collocated devices into a common data foundation for analysis and action. Key capabilities include Azure IoT Hub, Azure Digital Twins, Microsoft Defender for IoT, Azure IoT Operations, and Microsoft Fabric. Together, these tools help empower organizations to make data-driven decisions, boost operational efficiency, and scale AI across varied deployment environments.  

Industrial data acquisition and management: Microsoft’s focus on standards, ecosystem partnerships, and helping customers take advantage of existing investments are key pillars of its industrial data management strategy. Industrial data acquisition and management are challenging today due to the complexity of industrial environments. To help with this, Azure IoT Operations natively integrates with brownfield environments and enables high-velocity operational technology (OT)/IoT data collection and contextualization using Akri connectors. Once gathered, the data is stored in OneLake using Microsoft Fabric, allowing for unified modeling in a central location.   

Azure Arc-enabled Kubernetes extends these capabilities with open-standard APIs that integrate seamlessly with Azure’s cloud management graph (ARM graph), ensuring consistent security, auditing, and policy enforcement. Meanwhile, Azure Device Registry unifies asset management by representing edge assets as Azure resources which lays the groundwork for scalable application deployments. 

Real-time intelligence for smarter decisions: Microsoft’s strength in industrial data management is more than just technical, it is transformational. By cleaning, contextualizing, and curating OT/IoT data at the edge, Azure IoT Operations builds a solid foundation for real-time intelligence. Integrated with Microsoft Fabric and Azure Digital Twin Builder, this enables AI-enhanced decision making that helps customers optimize production quality, improve equipment reliability, and support sustainable operations.  

Integration with Microsoft Copilot in Azure: Microsoft is redefining intelligence with the integration of Copilot and generative AI capabilities across its IoT platform, especially Azure IoT Operations and Microsoft Fabric. With Copilot in Azure you can retrieve intelligent recommendations for operations management, advanced data analysis, and visualization. This empowers industrial teams to make faster and smarter decisions, whether optimizing workflows, interpreting complex datasets, or managing supervisory tasks.  

Cloud-to-edge integration with the adaptive cloud approach: Microsoft’s IoT platform enabled by Azure Arc’s adaptive cloud approach unifies hybrid, multicloud, edge, and IoT environments. This provides a consistent unified control plane for applications, data, and governance that meets industrial needs for scalability and operational efficiency.  

Secure by design, intelligent by default: Azure IoT Operations is designed with security at its core. This proactive approach is intended to reduce operational burden for users. Microsoft also has a fully integrated security suite, including Microsoft Defender for IoT, Microsoft Sentinel and Microsoft Entra. 

Shaping the future of digital operations 

Our roadmap will focus on expanding AI capabilities—including agentic and generative AI—across the Azure stack. We are committed to helping customers harness the full potential of their data, streamline operations, and innovate faster. We remain focused on evolving our platform to meet various industrial needs. As we continue to innovate, our priority is making it easier for customers and partners to build confidently on Azure. 

Microsoft has a robust partner ecosystem that can help ensure local expertise and tailored solutions for every industry, to unlock new opportunities and deliver even greater impact. Whether it is co-innovating on industry-specific solutions or scaling AI adoption globally, our partners are essential to helping customers build confidently on Azure.  

Learn more

Discover how Microsoft’s IoT offerings can enhance your operations. Explore the resources below for more information-

Explore Azure IoT portfolio.

Explore our unified data platform, Microsoft Fabric, and learn more about Digital Twin Builder in Microsoft Fabric.

Check out our IoT Partner Ecosystem.

Gartner, Magic Quadrant for Global Industrial IoT Platforms, By Scot Kim, Sudip Pattanayak, Emil Berthelsen, Sushovan Mukhopadhyay, Wam Voster, Akhil Singh, September 8, 2025.

Gartner does not endorse any vendor, product or service depicted in its research publications and does not advise technology users to select only those vendors with the highest ratings or other designation. Gartner research publications consist of the opinions of Gartner’s Research & Advisory organization and should not be construed as statements of fact. Gartner disclaims all warranties, expressed or implied, with respect to this research, including any warranties of merchantability or fitness for a particular purpose.

GARTNER is a registered trademark and service mark of Gartner, Inc. and/or its affiliates in the U.S. and internationally, Magic Quadrant is a registered trademark of Gartner, Inc. and/or its affiliates and is used herein with permission. All rights reserved.

This graphic was published by Gartner, Inc. as part of a larger research document and should be evaluated in the context of the entire document. The Gartner document is available upon request from here.
The post Microsoft named a Leader in the 2025 Gartner® Magic Quadrant™ for Global Industrial IoT Platforms  appeared first on Microsoft Azure Blog.
Quelle: Azure