The Agentic Productivity Stack: Orchestrating Multi-Agent Workflows with Microsoft Foundry

One agent answering questions is a chatbot. A team of agents handling document intake, approvals, and follow-up is a productivity engine. This session is a hands-on look at designing multi-agent workflows in Microsoft Foundry - when to split work across agents, how they hand off context, and how to keep the whole system observable and debuggable.

The Agent That Takes the First Ten Minutes of an Incident

Every incident starts the same way: someone gets paged, opens six tabs, and spends ten minutes assembling context before anyone can make a decision. That assembly work is well-shaped for an agent: bounded, repetitive, read-mostly - and it is where autonomous operations should start, rather than with the fantasy of an agent that fixes production by itself.
We build and run a triage agent on Azure that wakes on an alert, pulls the signal it needs from Azure Monitor and Log Analytics, correlates it against recent deployments and PRs, and produces a written incident brief with a ranked hypothesis and a citation for every claim it makes. Then it opens a draft PR for the one remediation we are willing to let it propose — and stops there, on purpose.
The second half is the part that makes this operable: what the agent is allowed to touch and how that boundary is enforced with a workload identity rather than a prompt instruction, what the blast radius looks like when the agent is wrong, how to evaluate a triage agent when every incident is a sample size of one, and the honest failure mode — an agent that writes a confident brief about the wrong service and sends three engineers in the wrong direction.
Attendees leave with the read-only-first pattern, the identity and approval boundaries worth setting before the first deploy, and a clear view of which parts of on-call should stay human.

Taming the Verbatim Chaos - with Semantic Intelligence and Agentic AI

Customer feedback at scale is noisy, unstructured, and deceptively simple to get wrong — most systems flatten rich verbatim text into a single sentiment score, losing the precise signals that drive operational decisions. This session shows how semantic intelligence techniques like aspect-based sentiment analysis can decompose free-text reviews into structured, grounded insights at the aspect level, and how an agentic AI layer can then reason over those insights to autonomously surface patterns, answer analytical questions, and trigger remediation workflows. Through a live end-to-end demo built on the Microsoft Azure data and AI platform, attendees will see a practical architecture for turning verbatim chaos into actionable, trustworthy intelligence.

Beyond Chatbots: Building Real-World Multi-Agent AI Systems with MS Foundry

What

This session explores how to design and implement multi-agent AI systems using MS Foundry Agent Service, where multiple specialized agents collaborate to solve complex real-world problems. The focus is on moving beyond single chatbots to role-based agents that work together with clear responsibilities.

Why

Many enterprise AI scenarios require coordination between capabilities such as data retrieval, reasoning, and task execution. A single agent often becomes difficult to scale and manage. Multi-agent architectures provide a structured way to divide responsibilities, improve reliability, and enable more intelligent automation.

How

Through a hands-on demonstration built using MS Foundry Agent Service, the session will show how agents can be designed with specific roles, connected together, and orchestrated to collaborate while maintaining context. The talk will highlight practical architecture patterns, communication flows, and key considerations for building scalable agent-based systems.

For Whom

This session is designed for AI engineers, developers, architects, and solution designers who want to understand how to build real-world agentic systems and implement collaborative AI agents in enterprise solutions using MS Foundry.

Key Takeaways
-Understand how multi-agent architectures enable specialized AI agents to collaborate instead of relying on a single monolithic agent.
-Learn how to define clear roles and responsibilities for agents such as retrieval, reasoning, and task execution.
-See how agent orchestration and communication patterns enable agents to work together while maintaining shared context.

Think Deeper with Claude: Designing Agentic AI with the New Copilot Studio and MS Foundry

In this session, we’ll explore how Claude models can be used in different parts of the Microsoft AI ecosystem, including Microsoft Copilot Studio and Microsoft Foundry. The focus will be on understanding where Claude fits best and how it can be used to build more capable AI experiences.

We’ll start by looking at the new Microsoft Copilot Studio experience and how it enables the creation of AI agents in a more streamlined and flexible way. Then we’ll move into Microsoft Foundry and explore how Claude can be used there for building and testing AI solutions with stronger reasoning and long-context capabilities.

Through live demos, you’ll see Claude in action in both environments, solving different types of problems—from structured agent experiences in Copilot Studio to more flexible AI use cases in Foundry.

By the end of the session, you’ll have a practical understanding of how Claude fits into Microsoft’s AI ecosystem and how to decide when and where to use it for building real-world AI solutions.

Key Takeaways

• Understand how Claude can be used across Microsoft Copilot Studio and Microsoft Foundry
• Learn where Claude performs best in real-world AI scenarios
• Get familiar with the new Copilot Studio experience for building AI agents
• See live demos of Claude handling different types of tasks and workflows
• Learn practical guidance on choosing the right AI tool for the right problem

Azure AI Foundry: From AI Experiments to Enterprise-Grade AI Agents

Enterprises are moving beyond AI pilots toward governed, production-ready AI agents—but fragmented tools and operational complexity often slow progress. In this session, we explore Azure AI Foundry, Microsoft’s unified platform for building, deploying, and operating enterprise-scale AI applications and agents. Learn how Foundry brings models, data, orchestration, security, and observability together to help organizations move from copilots to real, business-impacting AI systems

Connected Intelligence: Building Agents with Copilot Studio, AI Builder & AI Search

This workshop explores how to build and extend AI-powered agents using Microsoft Copilot Studio, AI Search, AI Builder and Power Automate to enhance user experiences and automate business processes. Attendees will gain practical insights through live demos, real-world use cases, and integration best practices.

Key Highlights:

-Introduction to Copilot Studio’s low-code/no-code capabilities for AI agent development
-Extending agent intelligence with AI Foundry
-Automating workflows and triggering actions using Power Automate
-Integrating agents with Power Platform, Dataverse, and enterprise systems
-Live demonstration of an AI-powered agent in action
-Best practices and real-world scenarios for deploying AI-driven solutions

Learning Objectives:
1. Develop and Deploy AI Agents – Learn how to design, build, and deploy AI agents using Microsoft Copilot Studio’s low-code/no-code capabilities.
2. Enhance AI Agents with Automation – Understand how to integrate AI Foundry for smarter decision-making and leverage Power Automate flows to automate workflows and trigger actions.
3. Integrate AI Agents with Enterprise Systems – Explore integration techniques with Power Platform, Dataverse, and other data sources to create seamless and efficient AI-driven solutions.

Azure AI Foundry: From AI Experiments to Enterprise‑Grade AI Agents

As organizations move beyond AI pilots and copilots, they face fragmented tools, governance challenges, and difficulty scaling AI into real business workflows. This session introduces Azure AI Foundry, Microsoft’s unified platform for building, deploying, and operating enterprise AI applications and agents. Attendees will see how Foundry brings together models, agent orchestration, secure RAG, and observability into a single control plane—and watch a live demo of an AI agent moving from prompt to production‑ready workflow.

- General understanding of cloud and AI concepts
- Familiarity with Azure and Microsoft ecosystem is helpful but not required
- No coding experience required for this session

Azure AI Foundry Workshop

This hands‑on workshop dives deeper into Azure AI Foundry as a production‑grade platform for enterprise AI agents. Participants will explore Foundry’s architecture, agent service, model catalog, secure RAG with Foundry IQ, and enterprise governance. Through guided exercises, attendees will design and implement an AI agent that integrates with enterprise data and workflows, while applying identity, observability, and cost controls from day one.

- Working knowledge of Azure fundamentals
- Basic understanding of LLMs, RAG, and AI agents
- Familiarity with at least one of the following: Python, REST APIs, or Azure services
- Optional: Azure subscription access for hands‑on exercises