The Hallway Track
35 tracked signals on microsoft-foundry.
Five agentic Claude capabilities now run on Azure-hosted Foundry, resolving enterprise data-residency trade-off
“That trade-off is now resolved. Structured outputs, Web search, Web fetch, MCP connector, and Tool search are available on deployments hosted on Azure.”
Microsoft Foundry assembles agents, tuning, evals, and OpenEnv into an owned reinforcement-learning loop that improves over time.
“the durable asset is not the model you rent, it is the learning loop you own”
Microsoft Foundry adds centralized tools, governance, evals, and an agent optimizer to make LangGraph agents enterprise-ready.
“Everyone is building agents, but that's not the hard part anymore. The hard part is integrating them into your business and governing them at scale.”
Microsoft Foundry adds enterprise agent distribution: publish to M365 Copilot/Teams, autopilot agents, and Agent-to-Agent.
“The past year was about building agents. The next year is about putting them to work.”
Agent Plugins 1.0 GA unifies MCP and skills into one cross-platform open standard
“One package, multiple clients, one thing to version.”
Microsoft Foundry's Hosted Agents, now in preview, runs your bring-your-own agent code at cloud scale.
“You can write that code, test it out locally, and then in hosted agents, we will go run it for you.”
Microsoft Foundry's Toolbox addresses authentication, tool sprawl, and governance as agent tool usage scales.
“the token usage context window got blown up really easily and quickly”
Anthropic's Claude models, including newly released Opus 4.8, are available in Microsoft Foundry for agentic coding.
“We've pretty well solved coding when you look at it from this metric's perspective.”
Microsoft Foundry introduces Foundry Managed Compute, a managed PaaS for deploying open-source and custom models.
“We have this construct called foundry managed compute which is think of it as a managed platform as a service where you just pick the GPUs.”
Foundry Observability uses OpenTelemetry to unify tracing across any agent framework or cloud without rewriting agents.
“Today I'm going to show you how to answer those questions in one place, foundry observability, not by rewriting your agents into one agent framework, but by adopting open telemetry instrumentation with a few lines of code and without changing your existing agent logic.”
Fireworks AI argues open-weight models now match closed frontier models for most enterprise tasks at far lower cost.
“for most enterprise use cases, the gap between openw weight models and frontier closed models has collapsed”
Microsoft Foundry's agent tracing and evaluations hit GA and now extend to any agent framework and deployment target.
“Shipping an AI agent is the easy part. Keeping it accurate, safe, and accountable in production is where teams get stuck.”
Microsoft Foundry Agent Service adds procedural memory so agents reliably reuse proven execution patterns in production.
“agents often know the right facts and still fail the task because they do not execute the right procedure”
Microsoft Foundry adds Toolboxes capabilities—Skills, Work IQ, Fabric IQ, Browser Automation, Tool Search, and Routines—to scale production agents.
“Tooling doesn’t break at a small scale—it breaks when teams move to production.”
Microsoft Foundry observability adds end-to-end tracing, evaluation, monitoring, and ROI for AI agents on any framework.
“agents are non-deterministic, creating new reliability and consistency challenges for developers and operators”
Microsoft Foundry adds reinforcement learning and a low-level training API to turn production agents into cheaper, faster models.
“Think of it as PyTorch as a service.”
Foundry Agent Service adds preview network egress controls to restrict where hosted agents can send outbound requests.
“A tool list is not a network boundary”
Most developers building agents lack visibility into what their agent does under the hood; observability and evals close that gap.
“you probably don't know what your agent is actually doing under the hood”
Microsoft and Anthropic webinar shows how to unlock Claude in Microsoft Foundry to build enterprise agents.
“I help engineering teams that are putting Claude into production.”
Foundry lets agents built with open-source frameworks deploy to production without rewriting, using OpenAI-compatible APIs and MCP.
“Changing the model target is configuration not a rewrite.”
Microsoft Foundry positions itself as the platform to build, govern, and manage continuously-improving agentic AI systems as models and costs shift.
“a year ago, building an AI app felt a lot more simple. You picked a model, you wire it up, and you ship it.”
Fireworks AI brings day-zero open-source model inference to Microsoft Foundry for production AI workflows.
“We serve around 13 trillion tokens per day and 180,000 requests per second.”
Azure Content Understanding adds GPT 5.2 support and GA SDKs at Build 2026 for unstructured content extraction.
“By building with Azure Content Understanding, DataSnipper is turning unstructured documents into structured, actionable data, directly inside Excel. Together, we are enabling faster reviews, reliable evidence, and AI you can trust.”
GitHub Copilot now supports external model providers when users exhaust native AI credits
“there are a ton of other options you can do to bring your own model and use that as inference or the brains behind the GitHub Copilot”
Azure SQL Database lets developers build vectors on operational data and ground LLMs like OpenAI and Anthropic via Microsoft Foundry.
“You can you can essentially talk to LLMs with the with the truth that you have in your operational data.”
Azure SQL Database lets developers build vector search on operational data and ground LLMs like OpenAI and Anthropic via Microsoft Foundry.
“you can essentially talk to LLMs with the truth that you have in your operational data”
Microsoft Foundry's agent platform unifies tracing, evaluation, and optimization to test non-deterministic AI agents end-to-end.
“The properties that makes agents so useful like they're stateful, they they're long horizon, they can plan, they can course correct, they interact with their environment through tools are also the ones that makes it very hard to test.”
Microsoft Foundry lets developers deploy advanced code-based agents via a layered runtime, intelligence, and collaboration stack.
“you can kind of choose the level of simplicity or control that you want for your agents”
Microsoft Foundry offers a single hub for pre-built and third-party agent tools with enterprise-grade scalability.
“Tool calling is what enables your agent to perform an action, and this is how your agents provide real business value.”
Microsoft Foundry portal lets developers build adaptable agentic AI apps using a microservices-style, per-agent approach.
“Agentic AI brings a microservices-based approach where every agent is a single unit of work that can be evolved independently without having to rewrite the entire system.”
Microsoft demos building a multi-agent customer insights system in VS Code running on Microsoft Foundry and connected to Fabric data.
“this is a front end website that's connected to an agent in the back end that runs in Microsoft Foundry”
Microsoft demos building offline AI-powered Windows apps using GitHub Copilot, WinUI, and the Windows AI stack.
“whether you're bringing your own model, whether you're looking for models on Hugging Face, or use some of these primitives uh primitives that we provide as part of the Windows SDK, we're trying to make it easy for you to effectively uh run AI models on Windows.”
Microsoft Foundry's catalog offers over 11,000 models and tools to filter them by scenario, task, and deployment.
“How do you narrow down to the best model for your scenario?”
Microsoft Foundry lets developers create multimodal AI agents that behave like people in a few clicks.
“Next year you're going to come and you're going to see agents that are no longer just chat bots. You're going to see agents that are like people.”
A Microsoft 'Budget Bytes' series teaches building AI apps on Azure SQL for under $25.
“you're going to learn how to build applications with AI and Azure SQL database, all within a budget of $25”