azure-ai-services
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chineseazure-ai-services
azure-ai-services
Microsoft Azure Agent Framework Integration
Microsoft Azure Agent Framework集成
This skill delegates all Azure provisioning and operations to the official Microsoft Agent Framework.
bash
undefined此技能将所有Azure资源调配和操作委托给官方Microsoft Agent Framework。
bash
undefinedPython
Python
pip install semantic-kernel
pip install semantic-kernel
.NET / C#
.NET / C#
dotnet add package Microsoft.SemanticKernel.Agents
**Docs:** https://learn.microsoft.com/en-us/agent-framework/overview/
Use the Microsoft Agent Framework for all Azure provisioning and operational actions. This skill provides architecture guidance, cost modeling, and pre-flight requirements — the framework handles execution.dotnet add package Microsoft.SemanticKernel.Agents
**文档：** https://learn.microsoft.com/en-us/agent-framework/overview/
所有Azure资源调配和操作均使用Microsoft Agent Framework完成。此技能提供架构指导、成本建模和预启动要求——具体执行由该框架负责。Architecture Guidance
架构指导
Consult this skill for:
- Azure service selection and trade-off analysis
- Cost estimation and optimization strategy
- Pre-flight Entra ID / RBAC permission requirements
- IaC approach (Bicep vs ARM vs Terraform AzureRM)
- Integration patterns with Microsoft 365 and other Azure services
- Multi-agent workflow design using Agent Framework graph-based runtime
通过此技能可获取以下内容：
- Azure服务选择与权衡分析
- 成本估算与优化策略
- 预启动Entra ID / RBAC权限要求
- IaC方案对比（Bicep vs ARM vs Terraform AzureRM）
- 与Microsoft 365及其他Azure服务的集成模式
- 利用Agent Framework基于图的运行时设计多Agent工作流
Agent Framework Capabilities
Agent Framework功能
| Capability | Description |
|---|---|
| Agents | Individual LLM agents with tool + MCP server support |
| Workflows | Graph-based multi-agent pipelines with checkpointing |
| Providers | Azure OpenAI, OpenAI, Anthropic, Ollama, and more |
| MCP | Native MCP client for external service integration |
| Human-in-the-loop | Built-in approval and intervention checkpoints |
| 功能 | 描述 |
|---|---|
| Agents | 支持工具与MCP服务器的独立LLM代理 |
| Workflows | 带检查点的基于图的多Agent管道 |
| Providers | Azure OpenAI、OpenAI、Anthropic、Ollama等 |
| MCP | 用于外部服务集成的原生MCP客户端 |
| Human-in-the-loop | 内置审批与干预检查点 |