Hands-on developer program

Build production AI agents on Azure AI Foundry

A 40-hour, weekend-only, live-online program for developers who want to move past single-shot prompting into stateful, tool-using, multi-agent systems — built with LangGraph, LangChain, and Microsoft's own Agent Framework, and shipped on Azure.

40
Total Hours
5
Weekends
10
Live Sessions
10
Hands-on Labs
⚡ Azure credits included for every participant — run every lab on real Foundry-hosted models
LangChain LangGraph Microsoft Agent Framework Microsoft Foundry Azure AI Search Azure AI Content Safety Azure Cosmos DB Azure Container Apps LangSmith / OpenTelemetry
Program overview

Practical, developer-first, and built to ship

Most GenAI courses stop at "call an LLM API." This program starts where agentic engineering actually begins: designing stateful graphs of reasoning and tool-use, grounding them in your own data, keeping them safe, comparing frameworks, and running them reliably in production on Azure — all built, session by session, with your own hands on the keyboard.

Who this is for

  • Software developers & backend engineers who write Python and want to build agentic systems, not just call chat completion endpoints
  • ML/data engineers moving from notebooks into production agent architecture
  • Tech leads evaluating LangGraph, Microsoft Agent Framework, and Azure AI Foundry for a real product

Prerequisites

  • Working Python (functions, classes, virtual environments)
  • Comfort with REST APIs and JSON
  • An Azure subscription (credits provided — see the Schedule section)
  • No prior GenAI / LangChain / Agent Framework experience required
✍️
PILLAR 01

Prompt Engineering

Structured prompting, function-calling schemas, few-shot & chain-of-thought patterns that hold up under real inputs.

🧩
PILLAR 02

Context Engineering

Context windows, chunking, and assembling system / tool / memory / retrieved context under a token budget.

🧠
PILLAR 03

Memory Management

Short- and long-term memory with LangGraph checkpointers, persisted on Azure Cosmos DB / Redis.

🔎
PILLAR 04

Retrieval (RAG)

Hybrid vector search on Azure AI Search, re-ranking, and grounded, cited answers.

🎯
PILLAR 05

Fine-Tuning

Supervised fine-tuning and model evaluation inside Microsoft Foundry, and knowing when to skip it.

🛡️
PILLAR 06

Guardrails & Observability

Content Safety, prompt-injection defenses, tracing, evals, and cost/latency monitoring in production.

Schedule

Five weekends, ten sessions, 40 hours

Every session is 4 hours, split across a focused teaching block and a hands-on lab, so each weekend leaves you with a working piece of an agent stack — not just slides. All sessions are delivered live, online.

WeekendDayHrsTheme
W1Saturday4h
Foundations — Agentic Architecture & Microsoft Foundry
LLM apps vs. agentic systems, ReAct & Plan-Execute patterns, the Foundry model catalog
W1Sunday4h
Prompt & Context Engineering
Structured output, function calling, context budgeting, prompt evaluation
W2Saturday4h
Memory Management with LangGraph
Checkpointers, short/long-term memory, Azure-backed persistence
W2Sunday4h
Retrieval-Augmented Generation on Azure
Azure AI Search, embeddings, re-ranking, grounded citations
W3Saturday4h
LangGraph Deep Dive
Graphs, cycles, subgraphs, streaming, human-in-the-loop interrupts
W3Sunday4h
Multi-Agent Systems & Guardrails
Supervisor/worker agents, Content Safety, prompt-injection defenses
W4Saturday4h
Model Fine-Tuning & Evaluation on Foundry
Dataset prep, fine-tuning jobs, side-by-side model evaluation
W4Sunday4h
Observability & Deployment
Tracing, evals, Azure Container Apps deployment
W5Saturday4h
Microsoft Agent Framework Fundamentals
Foundry-first Python SDK, agents, tools, MCP, agent sessions
W5Sunday4h
Agent Framework Workflows & Capstone
Graph workflows, the Harness, LangGraph vs. Agent Framework, final capstone
$

Azure credits included — for every participant, every lab

You'll deploy real models through Microsoft Foundry and provision real Azure services (AI Search, Cosmos DB, Container Apps) from Session 1. Azure credits are provided to each participant to cover this usage, so nothing in this program runs against a toy sandbox — you're learning on the same infrastructure you'll ship to.

Detailed curriculum

Every session, topic, and lab

Expand any weekend for the full breakdown. Each block builds directly on the one before it — by Weekend 5 you're comparing frameworks, not learning them from scratch.

01 Weekend 1 of 5

Foundations

Get a working agent talking to Microsoft Foundry, then make it reason on purpose.

Session 01Saturday · 4h

Agentic Architecture & Microsoft Foundry

Topics: LLM apps vs. agentic systems · ReAct, Plan-and-Execute & tool-use patterns · tour of the Microsoft Foundry model catalog, deployments & playground · Foundry SDK auth (Entra ID / keys) · wiring LangChain to Foundry-hosted models (GPT, Phi, Llama, Mistral)

Lab Deploy a Foundry model endpoint and call it from a LangChain chain; compare two models on the same task.
Tools: Microsoft Foundry · LangChain · Python SDK
Session 02Sunday · 4h

Prompt & Context Engineering

Topics: Prompt patterns (zero/few-shot, CoT, ReAct, self-consistency) · structured output & function/tool-calling schemas · LangChain prompt templates & output parsers · context-window budgeting, chunking & context-assembly strategies · prompt versioning & testing

Lab Build a structured-extraction agent with function-calling schemas and a 3-variant prompt-evaluation harness.
Tools: LangChain prompt templates · Pydantic output parsers
02 Weekend 2 of 5

Memory & RAG

Give the agent a memory that survives a restart, and facts it can actually cite.

Session 03Saturday · 4h

Memory Management with LangGraph

Topics: LangGraph state, threads & checkpointers · short-term vs. long-term memory · summarizing & entity memory · persisting agent state to Azure Cosmos DB / Azure Cache for Redis · multi-turn continuity

Lab Build a stateful support agent that remembers context across sessions, persisted on Cosmos DB.
Tools: LangGraph checkpointers · Azure Cosmos DB · Azure Cache for Redis
Session 04Sunday · 4h

Retrieval-Augmented Generation on Azure

Topics: Chunking & embedding strategy · Azure AI Search (vector, hybrid & semantic ranking) · Foundry embedding models · advanced retrieval (re-ranking, HyDE, self-query) · grounding responses with citations

Lab Ingest a document set → Foundry embeddings → Azure AI Search index → LangChain retriever → grounded, cited answers.
Tools: Azure AI Search · Foundry embedding models · LangChain retrievers
03 Weekend 3 of 5

Multi-Agent & Guardrails

Turn one agent into a team, then put a safety layer around what it's allowed to do.

Session 05Saturday · 4h

LangGraph Deep Dive

Topics: Graphs, nodes, edges & conditional routing · cycles & recursive reasoning · subgraphs & parallel branches · streaming · human-in-the-loop interrupts & approval gates

Lab Build a planner → executor → critic loop graph with a human-approval node before any external action.
Tools: LangGraph · streaming callbacks
Session 06Sunday · 4h

Multi-Agent Systems & Guardrails

Topics: Supervisor/worker & agent-handoff patterns · connecting agents to tools, Azure Functions & MCP servers · Azure AI Content Safety · prompt-injection & jailbreak defenses · PII redaction & output validation · tool-permission policies

Lab Extend Session 05's graph into a multi-agent team; add Content Safety filters and a tool-permission "circuit breaker."
Tools: Azure AI Content Safety · Azure Functions · MCP servers
04 Weekend 4 of 5

Fine-Tuning & Ops

Customize the model, then watch the whole stack in production.

Session 07Saturday · 4h

Model Fine-Tuning & Evaluation on Foundry

Topics: When to fine-tune vs. RAG vs. prompt-engineer · dataset prep for supervised fine-tuning · submitting & monitoring fine-tuning jobs in Microsoft Foundry · distillation basics · side-by-side model evaluation

Lab Fine-tune a small model on a custom dataset in Foundry and benchmark it against the base model using Foundry evaluation.
Tools: Microsoft Foundry fine-tuning & evaluation
Session 08Sunday · 4h

Observability & Deployment

Topics: Tracing with LangSmith / OpenTelemetry / Azure Monitor & Application Insights · cost, latency & token dashboards · automated regression evals & red-teaming · deploying agents to Azure Container Apps · Managed Identity & Key Vault for secrets

Lab Deploy your Weekend 3 multi-agent graph to Azure Container Apps with full tracing wired up.
Tools: LangSmith · Azure Monitor · Azure Container Apps · Key Vault
05 Weekend 5 of 5 · New

Microsoft Agent Framework

Learn Microsoft's own agent framework — see how the same agentic patterns you built in LangGraph translate to Microsoft's native, Foundry-first SDK, then finish with a capstone that ships to Azure.

🧭

Why this weekend exists: Microsoft Agent Framework is the direct successor to Semantic Kernel and AutoGen, built by the same teams. It combines AutoGen's simple agent abstractions with Semantic Kernel's enterprise features — session-based state management, type safety, middleware, and telemetry — and adds graph-based workflows for explicit multi-agent orchestration. Every developer shipping agents on Azure should know both this and LangGraph.

Session 09Saturday · 4h

Agent Framework Fundamentals

Topics: Agents vs. workflows — when to use which · Agent Framework as the successor to Semantic Kernel & AutoGen · building agents with the Python agent-framework package against Microsoft Foundry via FoundryChatClient · tools & hosted MCP servers · agent sessions for multi-turn state · middleware for intercepting agent actions

Lab Build a Foundry-backed agent with the Agent Framework Python SDK, attach a tool and a logging middleware, and run a multi-turn session.
Tools: agent-framework (Python) · Microsoft Foundry · MCP
Session 10Sunday · 4h

Graph Workflows, the Harness & Capstone

Topics: Graph-based workflows — type-safe routing, checkpointing, human-in-the-loop · the Agent Framework Harness (planning & todo tracking, context compaction, file access/memory, tool-approval policies, built-in observability) · multi-agent orchestration patterns · migrating from Semantic Kernel / AutoGen

Capstone Rebuild your Weekend 3 LangGraph planner → executor → critic workflow as an Agent Framework graph workflow with checkpointing and a human-approval step — then demo both side by side to the cohort.
Tools: Agent Framework Workflows · Harness · Azure Monitor
Logistics & enquiry

What you leave with

By the end of Weekend 5, you'll have a deployed, observable, guardrailed multi-agent system on Azure — built twice, in two frameworks — plus everything below.

Format

  • Live, instructor-led — 100% online
  • 5 consecutive weekends, Sat & Sun, 4 hrs/day (40 hrs total)
  • Small, focused cohorts for hands-on mentoring
  • Meet your instructor on demand — 1:1 time beyond the live weekend sessions

You receive

  • Azure credits to run every lab on real Foundry infrastructure
  • All 10 lab notebooks, sample datasets & reference agent graphs
  • Two deployed capstone projects — LangGraph and Agent Framework — you can extend post-course
  • Certificate of completion

Seats are limited per cohort

Bring your own Python skills — leave with a production agentic stack on Azure, built with both LangGraph and Microsoft Agent Framework, and the Azure credits to keep building on it.

Submit an enquiry