To assist these AI brokers turn into much more highly effective and deal with extra advanced duties, they want state-of-the-art fashions, built-in instruments, and built-in governance. At Microsoft Construct 2025, we’re unveiling 10 improvements in Azure AI Foundry to make this doable.
Software program improvement is present process a change. Within the outdated world, constructing software program was a protracted relay—weeks to plan, months to construct, and quarters to launch. Within the new world, AI-powered instruments flip concepts into prototypes in hours and manufacturing options in days. To attain this, builders want an end-to-end platform that seamlessly connects code, collaboration, and cloud. Microsoft is the one firm the place all three come collectively, with Visible Studio Code, GitHub, and Azure forming a unified, AI-native improvement expertise designed to empower each developer to form the long run with AI. We’re delivering a full-stack AI platform with built-in safety and belief—providing you with the whole lot it is advisable to construct and run AI-powered apps and brokers, from cloud to edge.
In simply two years, we’ve gone from early basis fashions to AI brokers able to advanced workflows. Microsoft Azure AI Foundry has already grown to assist greater than 70,000 clients, processing 100 trillion tokens final quarter, and powering 2 billion every day enterprise search queries. What started as an utility layer has now turn into a full-stack platform for constructing clever brokers that ship actual enterprise worth.
To assist these AI brokers turn into much more highly effective and deal with extra advanced duties, they want state-of-the-art fashions, built-in instruments, and built-in governance. Immediately at Microsoft Construct 2025, we’re unveiling 10 main improvements in Azure AI Foundry to make this doable.
1. New fashions
We’re increasing our catalog with cutting-edge fashions to provide builders extra selection. This consists of Grok 3 from xAI obtainable at this time, Flux Professional 1.1 from Black Forest Labs coming quickly, and Sora coming quickly in preview through Azure OpenAI in Foundry Fashions. We now have over 10,000 open-source fashions from Hugging Face obtainable in Foundry Fashions. We assist full fine-tuning (together with LoRA/QLoRA and DPO), so you possibly can tailor fine-tunable fashions to your wants. Moreover, we’re rolling out a brand new developer tier for fine-tuning—no internet hosting charges, only a easy technique to experiment and consider fine-tuning strategies with out the overhead.
2. Smarter mannequin system
Choosing the proper mannequin for every job is now simpler. Our new mannequin router mechanically selects the optimum Azure OpenAI mannequin in your immediate—boosting high quality whereas lowering prices. Beginning subsequent month, we’re extending reserved capability throughout Azure OpenAI and choose Foundry Fashions (like fashions from Black Forest Labs, DeepSeek, Mistral, Meta, and xAI), so that you get constant efficiency even beneath heavy load. All these fashions might be accessible by a unified API and Mannequin Context Protocol (MCP) server for Azure AI Foundry fashions, making it seamless to go from prototype to manufacturing.
3. Azure AI Foundry Agent Service
Azure AI Foundry Agent Service is now usually obtainable, empowering you to design, deploy, and scale production-grade AI brokers with ease. Greater than 10,000 organizations—together with leaders like Heineken, Carvana, and Fujitsu—have already used Azure AI Foundry to automate advanced enterprise processes with their very own information and information. This absolutely managed service takes care of infrastructure and orchestration, and it comes with ready-to-use templates, actions, and connectors to greater than 1,400 enterprise information sources (similar to SharePoint, Microsoft Cloth, and third-party programs), rushing up improvement of context-aware brokers. And with a number of clicks, you possibly can deploy your brokers into Microsoft 365 (Microsoft Groups and Workplace apps) or different platforms like Slack and Twilio—bringing brokers immediately into the instruments your workers use day by day.
4. Multi-agent orchestration
Actual-world workflows typically require a number of brokers working collectively. Azure AI Foundry now makes that simple, throughout any cloud. Brokers can name one another as instruments (related brokers), passing duties between specialised brokers to resolve advanced issues collaboratively. New multi-agent workflows present a stateful layer to handle context, deal with errors, and preserve long-running processes—nice for situations like monetary approvals or provide chain operations. We’ve additionally carried out open interoperability requirements—similar to Agent-to-Agent (A2A) communication, to allow totally different brokers to alternate data and coordinate duties, and the Mannequin Context Protocol (MCP) to allow brokers to share and interpret contextual information persistently. These requirements guarantee brokers can collaborate seamlessly throughout Azure, AWS, Google Cloud, and on-premises environments. Below the hood, we’re unifying our Semantic Kernel and AutoGen frameworks to assist this seamless agent orchestration.
And since Azure AI Foundry powers Microsoft Copilot Studio, you preserve a steady loop—from mannequin choice and fine-tuning to deploying pre-built brokers. As an example, Stanford Drugs is already utilizing our healthcare agent orchestrator in Azure AI Foundry alongside Microsoft Copilot Studio to streamline tumor-board conferences with customized medical workflows.
5. Agentic retrieval
We’re making data retrieval smarter to assist these superior brokers. Agentic retrieval in Azure AI Search is a brand new multi-turn question engine designed for advanced questions. It makes use of dialog context and an embedded LLM to interrupt down person queries into sub-queries, runs a number of searches in parallel, after which compiles a complete reply with citations. In early exams, this strategy improves reply relevance by as much as ~40% on advanced, multi-part questions. Now in public preview, agentic retrieval lets your brokers hook up with enterprise information extra successfully utilizing superior retrieval for correct, grounded solutions.
6. All the time-on observability
To carry brokers accountable in manufacturing, you want visibility into their efficiency. We’re previewing new Foundry Observability options that present end-to-end monitoring and diagnostics. You’ll get built-in metrics on latency, throughput, utilization, and high quality—plus detailed hint logs of every agent’s reasoning steps and gear calls. Throughout improvement, our Brokers Playground now reveals analysis benchmarks and traces that will help you refine prompts and logic. As you progress to CI/CD, we provide integrations with GitHub and Azure DevOps to include exams and guardrails. And in manufacturing, a unified dashboard (built-in with Azure Monitor) offers you real-time perception and alerts in your fashions and brokers.
7. Enterprise-grade identification for brokers
Microsoft Entra Agent ID is step one in managing agent identities in your group, providing you with full visibility and management over what your AI brokers can do. Microsoft Entra Agent ID assigns a singular, first-class identification to each agent you construct with Azure AI Foundry or Microsoft Copilot Studio. This implies your AI brokers get the identical identification administration as human customers—showing in your Microsoft Entra listing so you possibly can set entry controls and permissions for every agent. Quickly, safety admins will have the ability to apply Conditional Entry insurance policies, multi-factor authentication, and least-privilege roles to brokers, and monitor their sign-in actions. If an agent shouldn’t entry a useful resource, it will likely be blocked identical to an everyday person would.
8. Reliable AI built-in
Accountable AI is non-negotiable for us and our clients. We’ve added new capabilities to uncover, shield, and govern AI programs from the beginning. Agent Evaluators now mechanically test if an agent is following person intent and utilizing instruments accurately, flagging points for builders. An AI Purple Teaming Agent continuously probes your brokers for vulnerabilities or biases, so you possibly can repair weaknesses earlier than deployment. Our content material filtering has gotten smarter with “Spotlighting”—an enhancement to Immediate Shields that higher detects and mitigates malicious immediate injections (whether or not from customers or incoming information). We’ve additionally enabled enhanced guardrails to forestall brokers from revealing delicate data (PII) or straying off authorized duties. On the safety aspect, Azure AI Foundry integrates with Microsoft Defender for Cloud to lift alerts when threats happen. And to assist with compliance, we provide out-of-box integration with governance instruments like Credo AI, Saidot, and Microsoft Purview for monitoring mannequin efficiency, equity, and regulatory necessities. From day one, Azure AI Foundry equips you with the security, safety, and governance instruments to construct AI you (and your customers) can belief.
9. Foundry Native
Not all AI must run within the cloud—typically the very best answer is on the edge. Foundry Native is a brand new runtime for Home windows and Mac for AI fashions and brokers. With Foundry Native, you possibly can construct cross-platform AI apps that work offline, maintain delicate information regionally, and cut back bandwidth prices. This opens situations like manufacturing on a manufacturing facility flooring with spotty web, or area service apps that want AI in distant areas. We’re additionally integrating Foundry with Azure Arc. With the upcoming Azure Arc and Foundry integration, you possibly can handle and replace on-device AI deployments centrally. In brief, Foundry turns into your AI manufacturing facility—delivering generative AI the place your information is, whether or not that’s within the cloud or on-premises.
10. Future improvements for Foundry Labs
We’re exploring the subsequent frontiers with Microsoft Analysis in our Foundry Labs. One thrilling invention is Venture Amelie, powered by RD Agent from Microsoft Analysis, an autonomous agent that may construct full machine studying pipelines from a single immediate. Give it a job like “predict buyer churn from our dataset,” and Amelie will ingest information, prepare fashions, and produce a deployable answer—an experiment in AI creating AI.
We’re additionally rethinking how AI brokers work together with individuals and one another: Magentic-UI, now open-source, is an experimental human-centered agent that completes web-based duties, and TypeAgent is bringing long-term reminiscence to brokers, enabling them to retain and recall information over prolonged intervals. Within the scientific realm, new AI fashions like EvoDiff (for producing novel proteins) and BioEmu (for predicting how proteins change form) are being examined in Azure AI Foundry to speed up analysis in biology. These forward-looking initiatives present how Azure AI Foundry is frequently innovating—so that you’ll all the time have entry to the newest breakthroughs in AI.
The trail ahead with Azure AI Foundry
Be a part of us at Microsoft Construct 2025 to see these new capabilities in motion and find out how they’ll rework your corporation. We’re excited to work with you—our neighborhood of builders and clients—to form this new period of AI. Collectively, we’re making AI extra accessible, highly effective, and reliable for everybody. Study extra and get began with Azure AI Foundry.
Assets:
