microsoft/Learn-Microsoft-Agent-Framework-with-Foundry-ZavaShop-Supply-Chain-Workshop

microsoft/Learn-Microsoft-Agent-Framework-with-Foundry-ZavaShop-Supply-Chain-Workshop

Description: ZavaShop supply-chain workshop: 5 LABs on Microsoft Agent Framework + Microsoft Foundry, with shared data fixtures, AG-UI control tower, and a GitHub Copilot coding agent.

Language: Python

License: MIT

Stars: 25

Forks: 7

Open issues: 0

Created: 2026-05-27T06:57:32Z

Pushed: 2026-05-27T07:18:36Z

Default branch: main

Fork: no

Archived: no

README:

Learn Microsoft Agent Framework with Foundry — ZavaShop Supply‑Chain Workshop

> A Chinese edition of every README in this workshop is preserved alongside as README.zh.md.

This workshop walks you through the [Microsoft Agent Framework](https://learn.microsoft.com/en-us/agent-framework/) + [Microsoft Foundry](https://learn.microsoft.com/en-us/azure/foundry/agents/overview) (gpt-5.5) stack in five LABs, each one delivering a runnable feature on top of a single, continuous story.

> Two implementation tracks share the same story. Every LAB ships in both Python and .NET (C#). Same fixtures, same acceptance criteria, same Foundry model. Pick a track per LAB — you can switch between LABs.

---

0. The story — ZavaShop

ZavaShop is a fictional global e-commerce company. Its catalog covers three categories:

• 🏠 Home goods — bedding, decor, lighting
• 🌿 Garden & outdoor — garden tools, BBQ grills, outdoor furniture
• 🔌 Small home appliances — coffee machines, air purifiers, robotic vacuums

ZavaShop has 5 fulfillment centers (Seattle SEA-01, London LON-02, Shanghai SHA-03, São Paulo SAO-04, Dubai DXB-05) and partners with dozens of suppliers. Over the past year, the same pain points keep surfacing:

| Domain | Pain point | |--------|-----------| | Warehousing | Stock numbers are inconsistent across systems; warehouse supervisors are blocked by repetitive questions | | Procurement | Buyers manage 8+ ERP/supplier portals daily; quotes and contract clauses are scattered, with frequent approval errors | | Customer service | Reps don't remember VIP preferences (white-glove delivery, no cardboard, time windows…); chat models drift off-topic | | Fulfillment | Quote → stock check → approval → dispatch → finance is fully manual; one $10k+ exception per day | | Operations | Leadership wants a single dashboard, but every team builds their own |

The CTO has signed off on a Foundry-as-the-brain charter:

> *Every team rebuilds its workflow on Microsoft Agent Framework + Microsoft Foundry. The model is gpt-5.5. Workflows must orchestrate cross-team. The frontend is AG-UI + React, so the CEO can see everything from one console.*

You are the AI Platform Engineer at ZavaShop. The five LABs below are the five deliverables of this initiative.

---

1. The five LABs

| LAB | Story | Owner | What you build | Python SKILL | C# SKILL | |-----|-------|-------|---------------|--------------|----------| | [LAB01 — Inventory Agent](workshop/LAB01-inventory-agent/README.md) | Seattle DC supervisor Mei gets interrupted 60× a day | Mei | Agent Zara: function tools + HostedMCPTool + Thread | [agent-framework-azure-ai-py](.github/skills/agent-framework-azure-ai-py/SKILL.md) | [agent-framework-azure-ai-csharp](.github/skills/agent-framework-azure-ai-csharp/SKILL.md) | | [LAB02 — Procurement Toolbox](workshop/LAB02-procurement-toolbox/README.md) | Shanghai senior buyer Pierre juggles 8 systems | Pierre | Agent Pierre: Foundry Toolbox + Agent Skills + approval workflow | same as above (Toolbox / Skills / Threads) | same as above (Toolbox / Skills / Threads) | | [LAB03 — Customer Memory & Eval](workshop/LAB03-customer-memory-eval/README.md) | CS director Lin wants an agent that "remembers customers and is measurable" | Lin | Agent Aria: Foundry Memory + Evaluation + Red-Team | same as above (Memory / Evaluation) | same as above (Memory only — Evaluation + Red-Team SDKs are Python-only; reuse the Python scripts against your C# agent's endpoint) | | [LAB04 — Fulfillment Workflow](workshop/LAB04-fulfillment-workflow/README.md) | Fulfillment director Diego wants exception orders to self-orchestrate | Diego | Multi-agent ZavaFulfillment workflow: WorkflowBuilder + HITL + Checkpoint | [agent-framework-workflows-py](.github/skills/agent-framework-workflows-py/SKILL.md) | [agent-framework-workflows-csharp](.github/skills/agent-framework-workflows-csharp/SKILL.md) | | [LAB05 — Control Tower with AG-UI](workshop/LAB05-control-tower-agui/README.md) | The CEO wants a single dashboard that "feels alive" | CEO | ZavaControlTower AG-UI server + React frontend (covers all 7 AG-UI features) | [agent-framework-agui-py](.github/skills/agent-framework-agui-py/SKILL.md) | [agent-framework-agui-csharp](.github/skills/agent-framework-agui-csharp/SKILL.md) |

Every LAB ships:

• A story setup so you understand *why* you are building this
• A task list anchored to the SKILL's best practices
• Acceptance criteria so you can self-verify
• A story handoff that connects to the next LAB

---

2. Common prerequisites

2.1 Azure / Foundry

• An Azure subscription with the Microsoft Foundry service enabled
• A Foundry project with the gpt-5.5 model + text-embedding-3-small deployed
• Local Azure CLI logged in:

az login --use-device-code

2.2 Local environment — pick a track (or both)

The core fixtures and the Coding Agent are language-agnostic. Pick whichever LAB tracks you want to run.

Python option

• Python 3.10+
• Node.js 20+ (LAB05 frontend only)

python -m venv .venv
source .venv/bin/activate # macOS / Linux
# .venv\Scripts\activate # Windows PowerShell

pip install \
agent-framework \
agent-framework-azure-ai \
agent-framework-ag-ui \
azure-identity \
python-dotenv \
fastapi \
"uvicorn[standard]"

.NET option

• .NET 10 SDK (dotnet --version ≥ 10.0.100)
• Node.js 20+ (LAB05 frontend only)

The .NET track uses the prerelease Agent Framework NuGet packages — each C# SKILL lists the exact set per LAB. The common ones are:

Microsoft.Agents.AI
Microsoft.Agents.AI.Foundry
Microsoft.Agents.AI.Workflows # LAB 4 / LAB 5
Microsoft.Agents.AI.Hosting.AGUI.AspNetCore # LAB 5 server
Microsoft.Agents.AI.AGUI # LAB 5 client
Microsoft.Extensions.AI
Azure.AI.Projects
Azure.Identity
ModelContextProtocol # MCP clients

Each LAB's .csproj links the shared data helper:

>…