Defaults & paths ​
The default stack ​
The workshop examples all use one default stack so everyone can follow along. You are welcome to adapt them, see Choose your path below.
| Layer | Default | Why |
|---|---|---|
| Source control & workflow | GitHub | Repo, pull requests, and CI/CD (Continuous Integration / Continuous Deployment) in one place. |
| AI ecosystem | Azure + Microsoft Foundry (formerly Azure AI Foundry) | The default place we run and manage the model. |
| Language | Python | The most common language for agent tooling and the lab samples. |
| Terminal shell | Bash | All lab commands are written for bash. Git Bash, WSL, macOS Terminal, or any Linux shell will work. |
| Workshop site | VitePress | This site you are reading. |
"Default" means example, not requirement
Every concept (context engineering, memory, tools, MCP, HITL, A2A) is portable. The examples happen to use the stack above; the ideas work anywhere.
Choose your path ​
Pick the path that fits your goals and setup today. You can switch paths at any time.
| Path | Best when | What you do |
|---|---|---|
| Default path | You want hands-on practice and have the stack ready | Run every lab exactly as written. |
| Adapt to your own stack | You already use a different language/cloud/framework | Map each lab concept onto your tools; use our steps as a reference. |
| Observe conceptually | Your accounts aren't ready, or you prefer to watch | Read along, run nothing, and use the diagrams and checkpoints to follow the ideas. |
No wrong choice
If a lab isn't working on your machine, switch to observe for that hour and rejoin the default path at the next checkpoint. You will not fall behind.
Guidance by experience level ​
This day is designed for software developers who may be new to agentic AI. Use the row that matches you, and feel free to move between them.
| Level | You probably… | Focus on… |
|---|---|---|
| Beginner | Write code, but haven't built with AI agents | The plain-language definitions and the default path. Don't skip the "Why it matters" sections. |
| Intermediate | Have tried a chatbot or one tool call | Comparing the safe patterns (typed tools, memory boundaries, HITL) to what you've done before. |
| Advanced | Have built agents already | The stretch tasks in each segment and the failure modes, where these patterns break and why. |
What we will not cover ​
- A framework-by-framework comparison; we go deep on the default stack and keep concepts portable.
- Choosing a model provider or doing cost/latency benchmarking.