[ ABORT TO HUD ]
SEQ. 1
SEQ. 2
SEQ. 3
Azure AI Agent Service Overview
enterprise Agent Platform
The Azure AI Agent Service supersedes the classic OpenAI Assistants API, providing a production-ready platform for building, managing, and deploying AI agents.
2026 Agent Capabilities Updates
| Feature | Description | Impact |
|---|---|---|
| Hosted Agents (April 2026) | Persistent-state, VM-isolated agent compute with scale-to-zero | Agents resume with filesystem and session identity intact across restarts. Built-in versioning and VNet support for production workloads. |
| Toolboxes (GA) | Unified MCP-based tool management across frameworks | Dynamically selects the right tool per request instead of shipping every tool definition every time - configure once, use across Agent Framework, LangGraph, and any MCP-compatible client, with dramatically reduced token overhead. |
| Agent Service SDK v2.2.0 | Preview skills, toolboxes, and MCP endpoint support | Reusable agent capability bundles, unified tool management, and direct connection to remote MCP servers. |
| Memory Service | Managed long-term memory store (Preview) | Agents can persist and retrieve context across multiple sessions smoothly without custom DBs. |
| Foundry MCP Server | Cloud-hosted Model Context Protocol | Connect to cloud resources directly from IDEs (like VS Code) without local process management. |
| Voice Live | Native speech-to-speech runtime | Allows agents to converse in real-time with barge-in support. |
🆕 Build 2026: Microsoft Build 2026 (June 2–3) introduced further updates to the Foundry platform with a focus on agent-native multi-agent orchestration, expanding the Agent Service's capabilities for enterprise-scale autonomous workflows.
What an Agent Can Do
- Access tools - functions, code interpreter, file search, MCP servers
- Ground responses in your data via Azure AI Search
- Maintain long-term context with the Memory Service
- Delegate to other agents via Connected Agents
💡 Key Insight: The Agent Service manages the entire agent lifecycle - thread management, MCP tool execution, and state persistence (via Memory Service) - so you focus on defining agent behavior, not infrastructure.
FOUNDRY VERIFICATION
QUERY 1 // 2
What is the purpose of the Foundry MCP Server?
It provides visual analytics
It allows cloud-hosted Model Context Protocol connectivity directly from development environments like VS Code
It hosts custom websites
It is a specialized vector database