skills.rest
samelhousseini
samelhousseiniCOMMUNITY
Explore all skills by this author →
GitHub

hybrid-agents

Orchestrate Microsoft Agent Framework and Azure AI Foundry agents in hybrid workflows.

Updated Jan 15, 2026
Search Tags:#automation#MCP#multi-agent#orchestration#production-ready#Foundry#MAF
One-click install
npx skills add https://github.com/samelhousseini/microhacks --skill hybrid-agents
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hybrid-agents
Source: https://github.com/samelhousseini/microhacks/tree/main/.github/skills/hybrid-agents
Command: npx skills add https://github.com/samelhousseini/microhacks --skill hybrid-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-framework, azure-ai-agents, azure-ai-projects, azure-identity, python-dotenv, and includes scripts (resource) components.

What problem does it solve?

This Skill enables teams to design and run production-grade multi-agent workflows that combine local client-side orchestration with cloud-managed agents, enabling scalable, privacy-conscious AI automation.

Core Features & Use Cases

  • Multi-agent orchestration: supports sequential, parallel (fan-out/fan-in), and hybrid patterns across Microsoft Agent Framework and Azure AI Foundry.
  • MCP integration: enables tool calls and approvals for external services within agent workflows.
  • Production resilience: includes retry with backoff, circuit breaker, and workflow checkpointing for long-running processes.
  • Use Case: implement a cloud+local data processing pipeline that runs locally for sensitive data and leverages cloud reasoning for scale.

Quick Start

Run the hybrid workflow demo with real Azure credentials. Example steps:

  1. Configure environment variables (PROJECT_ENDPOINT, AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_CHAT_DEPLOYMENT_NAME, MODEL_DEPLOYMENT_NAME).
  2. Install dependencies from requirements.txt.
  3. Run the v1 demo: python scripts/hybrid_workflow_demo.py
  4. Or run the v2 demo: python scripts/hybrid_workflow_demo_v2.py

Frequently Asked Questions about hybrid-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate multi-agent workflows across local and Azure AI Foundry cloud agents?▼

Multi-agent orchestration across local and Azure AI Foundry cloud agents is handled by combining Microsoft Agent Framework client-side agents with cloud-managed agents. The Skill supports sequential, parallel fan-out/fan-in, and hybrid patterns for enterprise automation tasks.

Can I integrate MCP tool calls and approvals into Azure AI agent workflows?▼

MCP integration is supported within Azure AI agent workflows to enable tool calls and approvals for external services. This allows production-ready multi-agent orchestration to interact with external tools while maintaining workflow state and error handling.

What's the best way to add retries and circuit breakers to multi-agent automation pipelines?▼

Production resilience for multi-agent automation pipelines is achieved through retry with backoff, circuit breakers, and workflow checkpointing. These patterns ensure long-running processes maintain state and recover gracefully from transient failures.

How do I run a hybrid cloud and local data processing pipeline for sensitive information?▼

A hybrid data processing pipeline runs locally for sensitive data while leveraging cloud reasoning for scale. Configure environment variables like PROJECT_ENDPOINT and AZURE_OPENAI_ENDPOINT, install dependencies, then execute the hybrid workflow demo script.

Do I need Azure credentials to orchestrate Microsoft Agent Framework client-side agents?▼

Azure credentials are required for orchestration involving Azure AI Foundry cloud agents. You must configure environment variables including PROJECT_ENDPOINT, AZURE_OPENAI_ENDPOINT, and deployment names before running the hybrid workflow demo scripts.

Does multi-agent orchestration support parallel fan-out and fan-in execution patterns?▼

Multi-agent orchestration supports parallel fan-out and fan-in execution patterns alongside sequential and hybrid workflows. These patterns span Microsoft Agent Framework and Azure AI Foundry, enabling scalable cloud plus local automation.

Related Skills

Explore More Software Engineering Skills→
EmeaAppGbbEmeaAppGbb

microsoft-agent-framework

Build and orchestrate AI agents with Microsoft Agent Framework.

Official
Intermediate
MysMonMysMon
2

error-recovery

Automate checkpoint-based recovery and error handling for multi-step agent workflows.

Community
Advanced
kinfeykinfey

agent-framework-azure-ai-csharp

Build Microsoft Foundry AI agents in .NET with the Microsoft Agent Framework SDK.

Community
Advanced
markpittmarkpitt
22

agent-patterns

Orchestrate modular AI agent patterns with deterministic and dynamic workflows.

Community
Advanced