Microsoft Reactor Sydney

The session will introduce the concept of skills, explain how they differ from general agent instructions, and demonstrate how they enable agents to perform specialised tasks with greater accuracy and consistency.

Through a live demonstration, attendees will learn how to:

• Create and configure skills
• Define activation instructions
• Incorporate guidelines and examples
• Test skill behaviour in real-world scenarios

By the end of the session, participants will have a clear understanding of how skills can be leveraged to:

• Improve agent capabilities
• Promote reusable business logic
• Build intelligent AI solutions using Microsoft Copilot Studio

AI-assisted development is transforming how engineers build and maintain software.
This session showcases practical workflows using GitHub Copilot and VS Code, covering code generation, debugging, testing, documentation, and productivity techniques you can apply in your day-to-day work.

Attendees will learn how to enhance their development process with AI while maintaining efficiency, quality, and responsible practices.

Key takeaways:

• Effective prompting for software development
• AI-assisted debugging and testing
• Developer productivity workflows
• Responsible AI usage practices

What happens when you take AI out of the lab and deploy it in the Australian outback?

Join Microsoft MVP Daniel Brown, live from the opal fields of Coober Pedy, South Australia, as he explores how OpalAI was built to use artificial intelligence to help identify opal-bearing material during mining operations.
Using OpalAI as a real-world case study, we'll explore the complete journey:
- Collecting and preparing field data
- Building an AI solution with Microsoft Azure
- Integrating AI into an application
- Deploying AI in a challenging real-world environment

We'll also examine the practical engineering challenges that emerge outside controlled environments, including:
- Changing lighting conditions
- Dust and environmental interference
- Camera positioning
- False positives
- Confidence thresholds
- Ongoing model improvement

The session will culminate in a live field demonstration, running material through OpalAI from an active opal claim in Coober Pedy to see whether AI can identify potential opal in real time.

Key Takeaways
Developers will leave with practical lessons for designing, building, and deploying AI applications that connect:
- Software
- Artificial Intelligence
- The Physical World