Hosting

• Key points are in the visual diagram above.

Understanding Hosting helps you build reliable, scalable agent applications instead of fragile demos.

Think of Hosting as a specialized capability in your Microsoft Agent Framework engineering toolkit.

Scenario

A production team in Microsoft Agent Framework uses Hosting to handle a real user request — reducing manual work and improving response quality with proper validation and logging.

Solution

In Microsoft Agent Framework, apply Hosting to this scenario: A production team in Microsoft Agent Framework uses Hosting 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.

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 Hosting (e.g. model, temperature, top_k, or tool name), observe the difference in output, and write 2–3 sentences explaining what changed.

Highlighted lines show where Hosting happens in the code.

1# Hosting — 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 Hosting8    model="gpt-4o-mini",9    messages=[10        {"role": "system", "content": "You explain hosting clearly."},11        {"role": "user", "content": f"What is hosting?"},12    ],13    temperature=0,14)15print(response.choices[0].message.content)  # show output for debugging

• Skipping evaluation for Hosting before production
• No logging or tracing around maf hosting steps
• Ignoring cost and latency implications

Quick recap — the most important points from this module.