Class Details
This four-day private online class is for software architects and engineers who build, orchestrate and operate agentic applications with Microsoft Foundry and the Microsoft Agent Framework.
The class starts with the Foundry essentials and the MCP servers the agents call, covers server-side agents in the Foundry Agent Service and code-first agents in the Agent Framework, composes them into workflows and multi-agent orchestrations, hosts them, and makes them measurable and safe with evaluation, observability, guardrails and governance.
Audience
- Software architects and engineers who build agentic AI solutions
- AI pro-code developers who build agents in Python or C#
Prerequisites
- Python, C# and TypeScript
- A GitHub account
- An Azure subscription with access to Microsoft Foundry
- Azure development skills are helpful
Curriculum
Module 1: Foundry Essentials for Agent Developers
- Microsoft Foundry: Projects & Resources
- Model Deployments & Model Router
- Foundry SDK & Microsoft.Extensions.AI
- Responses API: Conversations & Streaming
- Foundry Toolkit & Foundry MCP Server
- Context Engineering: Budgets, Compaction & Caching
Module 2: MCP Servers, Security & Hosting
- MCP Servers: Tools, Resources & Prompts
- Transports & MCP Inspector Debugging
- MCP Authorization: OAuth 2.1 & PRM
- Hosting MCP on Azure Functions
- MCP Resilience: Retry & Circuit Breaker
- Foundry Toolbox: Managed MCP Endpoints
Module 3: Foundry Agent Service: Tools, Knowledge & Memory
- Prompt Agents: Versions & Conversations
- Code Interpreter, File & Web Search
- Browser Automation & Computer Use
- Foundry IQ: Knowledge Bases & Retrieval
- Advanced RAG: Hybrid Search & Reranking
- Agent Memory: User & Procedural Memory
- Stateful Agentic Loops: Plan & Resume
- Voice Agents: Voice Live API
Module 4: Agent Framework: Agents, Tools & Skills
- Chat Clients: Foundry, OpenAI & Claude
- AgentSession: State & Persistence
- Context Providers & Long-Term Memory
- Middleware: Agent, Function & Chat
- Function Tools, MCP & Approvals
- Agent Skills: SKILL.md & Progressive Disclosure
- Harness Agent: Plan, Execute & Compaction
Module 5: Workflows & Multi-Agent Orchestration
- Workflows: Executors, Edges & Supersteps
- Checkpointing & Human-in-the-Loop Requests
- Sequential, Concurrent & Handoff Orchestration
- Group Chat & Magentic Orchestration
- Task Decomposition: Planner & Waves
- Resilient Orchestration: Quorum & Supervisors
- Declarative YAML & Functional Workflows
Module 6: Hosting, Durable Agents & Protocols
- Hosted Agents: Containers & Agent Identity
- Foundry Routines: Schedules & Event Triggers
- azd AI Agent: Deploy & Monitor
- Durable Agents: Functions & Task Scheduler
- Self-Hosting: ASP.NET Core & Responses
- A2A Protocol: Agent Cards & Endpoints (optional)
- Enterprise A2A: Registry & Shared State (optional)
- AG-UI & CopilotKit: Web Front Ends (optional)
Module 7: Evaluation, Observability & Optimization
- Tracing: OpenTelemetry & Application Insights
- Agent Evaluators: Task Adherence & Tools
- Evaluation Suites: Judges & Baselines
- Continuous Evaluation & AI Red Teaming
- Agent Optimizer: Instructions & Tool Tuning
- Performance & Cost: Routing & Caching
- Incident Response: Replay & Postmortem
Module 8: Security, Governance & Delivery
- Guardrails: Prompt Shields & Intervention Points
- Prompt Injection: Layered Defenses
- Entra Agent ID: On-Behalf-Of Flows
- Zero Trust: Tenant Isolation & Secrets
- CI/CD: GitHub Actions Quality Gates
- Agent Lifecycle: Versions, Quotas & Retirement
- Responsible AI: Fairness Probes & Audit
Class Logistics
Day rate
1.250 EUR · online only, +20% VAT, reverse charge possible
Material
Labs, decks · 35 EUR per day per participant
Max Users
16
Lab Requirements
GitHub Codespaces / DevContainer
AI Harness: Bring your own
AI Harness: Bring your own