Learning by Patrik

Orchestrate a multi-agent solution using the Microsoft Agent Framework | AI-103 | Episode 14

A single agent can handle one task well; multi-agent orchestration coordinates specialized agents to solve larger tasks together. The Microsoft Agent Framework provides orchestration patterns that can be implemented directly in application code.

Know which orchestration pattern fits which execution flow:

Pattern	Execution model	Best fit
Sequential	A → B → C	Fixed pipeline; each output feeds the next agent
Concurrent	A → B/C/D → merge	Independent work that can run in parallel
Handoff	A → dynamically chosen specialist	Routing/delegation based on the request
Group Chat	Manager selects agents iteratively	Collaborative reasoning with shared conversation context
Magnetic	Orchestrator dynamically plans execution	Complex tasks where the path is not known upfront

Key distinction: Sequential and concurrent workflows have largely predictable structures. Handoff, group chat, and especially magnetic orchestration introduce increasingly dynamic agent selection and execution.
A simple sequential workflow illustrates the core programming model:

# 1. Define specialized agents
summarizer = chat_client.as_agent(...)
classifier = chat_client.as_agent(...)
action     = chat_client.as_agent(...)

# 2. Define their execution order
workflow = SequentialBuilder(
    participants=[summarizer, classifier, action]
).build()

# 3. Run the orchestration
await workflow.run(user_input)

Here, the summarizer → classifier → action order is explicit, and each agent runs in turn.
Remember: first define the agents and their capabilities, then select an orchestration pattern matching the required execution and collaboration model.

Agents

Orchestration

Multiagent

Azure

AgentFramework