Hands-on workshops

Moving an AI agent from a fragile prompt playground to a production-ready cloud deployment requires a solid architectural foundation. Microsoft Foundry changes the paradigm by introducing a managed, containerised runtime for custom agent code via Hosted Agents, alongside centralised runtime tool discovery with Foundry Toolboxes.

This 3-hour, hands-on workshop is designed for engineers, architects, and technical leaders who want to learn how to stand up, secure, and scale production-grade agent environments. Leveraging pre-built, community-vetted labs, we will step through local verification, configure centralized toolboxes via the Model Context Protocol (MCP), and ground our agents using Foundry IQ retrieval. Best of all, we will focus heavily on architecture, configuration, and control-plane deployment — meaning no deep, from-scratch coding is required.

Agentic Workflows bring Agentic AI into the repository itself. Instead of prompting an assistant one question at a time, you get a version-controlled teammate that triggers on real events: a schedule, a new issue, a PR, or a Check run. It reasons about your codebase, and takes bounded, reviewable actions like triaging issues, drafting fixes, or refreshing docs.

It's Agentic Engineering in practice. You get the autonomy and tool-use of Agentic AI, wrapped in real guardrails. The agent works in read-only mode, so it can't change anything directly. Every change it proposes flows through capped, validated safe-outputs, which keeps humans in control of the final call. The shift is from AI that answers to AI that does work: autonomous, auditable, and quietly moving your project forward around the clock.

This hands-on workshop, Building GitHub Agentic Workflows, runs 90 minutes and works solo or in pairs — aimed at developers and maintainers comfortable with Git and GitHub Actions. Prerequisites: a GitHub account and a test repo you own, the gh CLI installed and authenticated (gh auth login), the gh-aw extension installed (gh extension install githubnext/gh-aw), Copilot access enabled, and the repo setting Settings → Actions → General → "Allow GitHub Actions to create and approve pull requests" pre-flipped.

Aspire is an agent-ready, code-first tool for composing, debugging, and deploying distributed applications — an opinionated distributed application development framework. We'll use Aspire to bootstrap, implement, debug, and integrate an AI-featured application using ASP.NET, the Microsoft Agent Framework, the Model Context Protocol, containers, GitHub Copilot, and Visual Studio Code.

Prerequisites: the .NET CLI, the Aspire CLI, GitHub Copilot, Docker, and the Azure Functions CLI.

Modern cloud environments generate more alerts, telemetry, and operational data than teams can reasonably process. In this hands-on workshop, we will work through a realistic cloud incident and use AI-powered SRE agents to investigate the issue, correlate signals across systems, identify likely root causes, and recommend or take corrective action. The session will combine a short introduction with guided, practical exercises, giving attendees firsthand experience of how agentic AI can support incident response, reduce operational toil, and help teams resolve issues faster. Participants should bring a laptop and be ready to get hands-on.

Most MCP setups in production have no audit trail, no policy enforcement, and no signed evidence of what the agent actually did. That's fine for prototypes — and it's exactly why security teams block these systems from going further.

This half-day workshop takes a working MCP setup and instruments it end-to-end: tamper-evident audit logs, Ed25519-signed receipts of every tool call, and a policy engine that blocks or allows at the proxy layer. You'll leave with a running pipeline you could demo to a security stakeholder on Monday.

We'll use agent-receipts (open-source, MIT) as the demo audit tool, but cover the alternatives — Pipelock, mcp-firewall — and discuss when each fits. The goal isn't to sell one tool; it's to give you a concrete, working starting point for the audit and policy conversation that's currently blocking your agentic features in production.

AI agents are increasingly expected to write code, execute commands, and solve complex problems autonomously. The challenge isn’t making them more capable—it’s making them safe and production ready.

In this hands-on workshop, you’ll build an AI agent using the OpenAI Agents SDK and Temporal, learning how sandboxed execution gives agents the freedom to act safely, while durable execution ensures work survives failures, restarts, human approvals, and long-running tasks.

You’ll leave with a working application and practical patterns for building resilient, production-ready agentic systems.