Durable Execution & HITL
~3 min read
Concept & How It Works
- Key points are in the visual diagram above.
Why Does It Exist?
Understanding Durable Execution & HITL helps you build reliable, scalable agent applications instead of fragile demos.
Real-World Analogy
Think of Durable Execution & HITL as a specialized capability in your Microsoft Agent Framework engineering toolkit.
Visual Workflows
What is Durable Execution & HITL?
Example
Scenario
A production team in Microsoft Agent Framework uses Durable Execution & HITL to handle a real user request — reducing manual work and improving response quality with proper validation and logging.
Solution
In Microsoft Agent Framework, apply Durable Execution & HITL to this scenario: A production team in Microsoft Agent Framework uses Durable Execution & HITL to handle a real user request — reducing manual work and improving response quality with proper validation and logging. Identify the inputs, run the technique, validate the output, and note one thing you would monitor in production.
Practice Task
Do this before moving to the next module — reading alone is not enough.
Open the Code Walkthrough below and run it locally. Change one parameter related to Durable Execution & HITL (e.g. model, temperature, top_k, or tool name), observe the difference in output, and write 2–3 sentences explaining what changed.
Code Walkthrough
Highlighted lines show where Durable Execution & HITL happens in the code.
1# Durable Execution & HITL — minimal example2from openai import OpenAI3
4client = OpenAI() # create API client5
6# Ask the model to explain this topic7response = client.chat.completions.create( # core API call for Durable Execution & HITL8 model="gpt-4o-mini",9 messages=[10 {"role": "system", "content": "You explain durable execution & hitl clearly."},11 {"role": "user", "content": f"What is durable execution & hitl?"},12 ],13 temperature=0,14)15print(response.choices[0].message.content) # show output for debuggingCommands to Remember
Commands to Remember
pip install agent-framework # Microsoft Agent Frameworkpip install autogen-agentchat # AutoGen (legacy / migration)
Common Mistakes
- Skipping evaluation for Durable Execution & HITL before production
- No logging or tracing around maf durable execution steps
- Ignoring cost and latency implications
Cheat Sheet
Quick recap — the most important points from this module.
Cheat Sheet
quick ref- •Durable Execution & HITL
- •Microsoft Agent Framework
