Building AI agents often involves far more than writing code: configuring tools, debugging behavior, testing integrations, and deploying to production. In this talk, we'll explore how GitHub Copilot, Microsoft Foundry Skill, and Foundry Toolkit enable an end-to-end agent development workflow entirely within Visual Studio Code.
If you're following along during a live session:
- Review the Caldova pharmaceutical business scenario
- Explore the agent implementation in
src/ - Review the supporting sample inputs in
data/
If you're learning at your own pace:
- Clone this repository
- Review the sample agent implementation in
src/ - Use the supporting inputs in
data/to explore the scenario
By the end of this session, you will be able to:
- Explain how GitHub Copilot, Microsoft Foundry Skill, and Foundry Toolkit support the AI agent development lifecycle in Visual Studio Code
- Use GitHub Copilot and Microsoft Foundry Skill to configure and debug an AI agent in Visual Studio Code
- Test agent integrations and prepare an AI agent for production deployment from Visual Studio Code
- GitHub Copilot
- Microsoft Foundry Skill
- Foundry Toolkit
- Visual Studio Code
Pick your next step based on your learning style:
| Resource | What you'll get |
|---|---|
| Session Recording | A recording of session LTG232 by the session creator |
| Microsoft Learn | Official documentation and guided learning paths on these topics |
| AI Tour 2027 Resource Center | Additional session repos and materials from AI Tour 2027 |
| Microsoft Foundry Community | Connect with other learners and experts in our Discord community |
The Microsoft Learn MCP Server gives your AI agent direct access to Microsoft's official documentation — grounded, up-to-date answers about the topics in this session.
GitHub Copilot CLI — Install with:
copilot plugin install microsoftdocs/mcpVS Code — One-click install:
For more information, visit the Learn MCP Server repo.
 Carlotta Castelluccio 📢 |
Presenters and re-delivery partners can find the deck, recordings, presenter
notes, and delivery guidance in delivery-resources/.
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
Any use of third-party trademarks or logos are subject to those third-party's policies.