agent-framework-workflows-py

Construct and execute multi-step Microsoft Agent Framework workflows in Python.

34|17|Updated May 27, 2026
One-click install
npx skills add https://github.com/microsoft/Learn-Microsoft-Agent-Framework-with-Foundry-ZavaShop-Supply-Chain-Workshop --skill agent-framework-workflows-py-microsoft
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-framework-workflows-py
Source: https://github.com/microsoft/Learn-Microsoft-Agent-Framework-with-Foundry-ZavaShop-Supply-Chain-Workshop/tree/main/.github/skills/agent-framework-workflows-py
Command: npx skills add https://github.com/microsoft/Learn-Microsoft-Agent-Framework-with-Foundry-ZavaShop-Supply-Chain-Workshop --skill agent-framework-workflows-py-microsoft

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-framework, agent-framework-orchestrations, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables you to create deterministic multi-step, multi-agent workflows in Python using the Microsoft Agent Framework, which simplifies complex workflow orchestration and execution.

Core Features & Use Cases

  • Multi-Agent Workflows: Compose workflows with multiple agents, handling complex logic and execution flows.
  • Conditional Routing: Implement conditional logic within workflows to route based on specific criteria.
  • Human-in-the-Loop: Integrate human interaction into workflows with request-info and response-handling capabilities.
  • Checkpointing and Resume: Save and resume workflows from specific checkpoints for robust execution.
  • Use Case: Build a workflow that coordinates various agents to process and review a customer's support ticket, integrating human input when necessary.

Quick Start

Use the agent-framework-workflows-py skill to build a simple workflow that extracts text and reverses it.

from agent_framework import Executor, WorkflowBuilder

@executor
async def reverse_text(text: str) -> str:
    return text[::-1]

workflow = WorkflowBuilder(start_executor=reverse_text).build()
result = await workflow.run("hello world")
print(result)

Frequently Asked Questions about agent-framework-workflows-py

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

FAQPage Schema
How do I build multi-agent workflows in Python with conditional routing?

The Microsoft Agent Framework enables multi-agent workflows in Python with built-in conditional routing to direct execution paths based on specific criteria, simplifying complex orchestration logic.

Can I add human-in-the-loop interactions to a Python agent workflow?

Yes, you can add human-in-the-loop interactions to a Python agent workflow by using the framework's request-info and response-handling capabilities to integrate human input directly into the execution flow.

How does checkpointing work for Python multi-agent workflows?

Checkpointing in Python multi-agent workflows saves the execution state at specific points, allowing you to pause and resume complex orchestration workflows for robust, persistent execution.

Do I need specific libraries to orchestrate multi-agent workflows in Python?

Yes, orchestrating complex multi-agent workflows in Python requires the agent-framework and agent-framework-orchestrations libraries to handle the execution logic and deterministic routing.

What is the best way to coordinate multiple agents to process a support ticket in Python?

The best way to coordinate agents processing a support ticket in Python is using the Microsoft Agent Framework to build a deterministic workflow that integrates human input and manages conditional review logic.