Declarative workflows allow you to define multi-agent orchestration patterns in YAML, including:

• Variable manipulation and state management
• Control flow (loops, conditionals, branching)
• Agent invocations
• Human-in-the-loop patterns

See the main workflows README for the list of available samples.

pip install agent-framework-declarative

Each sample directory contains:

• workflow.yaml - The declarative workflow definition
• main.py - Python code to load and execute the workflow
• README.md - Sample-specific documentation

To run a sample:

cd <sample_directory>
python main.py

A basic workflow YAML file looks like:

name: my-workflow
description: A simple workflow example

actions:
  - kind: SetValue
    path: turn.greeting
    value: Hello, World!

  - kind: SendActivity
    activity:
      text: =turn.greeting

• SetValue - Set a variable in state
• SetVariable - Set a variable (.NET style naming)
• ResetVariable - Clear a variable

• If - Conditional branching
• ConditionGroup - Multi-way branching
• Foreach - Iterate over collections
• GotoAction - Jump to labeled action

• SendActivity - Send text/attachments to user

• InvokeAzureAgent - Call an Azure AI agent

• InvokeFunctionTool - Call a registered Python function

• Question - Request user input
• RequestExternalInput - Request external data/approval