Copyright (c) 2026 MindMesh Academy. All rights reserved. This content is proprietary and may not be reproduced or distributed without permission.

3.1.2. Microsoft Foundry Agent Service

  • Concept: Azure's managed service for building AI agents
  • Purpose: Simplify agent development with pre-built infrastructure
  • Benefit: Focus on agent logic, not infrastructure
To create an agent that performs actions (scheduling meetings, sending notifications):

Solution: Add custom functions

# Custom function definition
tools = [
    {
        "type": "function",
        "function": {
            "name": "schedule_meeting",
            "description": "Schedule a meeting on the user's calendar",
            "parameters": {
                "type": "object",
                "properties": {
                    "title": {"type": "string", "description": "Meeting title"},
                    "datetime": {"type": "string", "description": "ISO datetime"},
                    "attendees": {"type": "array", "items": {"type": "string"}}
                },
                "required": ["title", "datetime"]
            }
        }
    }
]
Why custom functions?
  • ✅ Enables dynamic action execution
  • ✅ Programmatic integration with external systems
  • ❌ Static templates lack flexibility
  • ❌ Default capabilities can't perform specific actions
  • ❌ Pre-trained chatbots need customization for actions