GenAI Semantic Conventions

• Key points are in the visual diagram above.

Understanding GenAI Semantic Conventions helps you build reliable, scalable agent applications instead of fragile demos.

Think of GenAI Semantic Conventions as a specialized capability in your Eval Engineering & Observability engineering toolkit.

Scenario

A production team in Eval Engineering & Observability uses GenAI Semantic Conventions to handle a real user request — reducing manual work and improving response quality with proper validation and logging.

Solution

In Eval Engineering & Observability, apply GenAI Semantic Conventions to this scenario: A production team in Eval Engineering & Observability uses GenAI Semantic Conventions 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 GenAI Semantic Conventions (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 GenAI Semantic Conventions happens in the code.

1# GenAI Semantic Conventions — 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 GenAI Semantic Conventions8    model="gpt-4o-mini",9    messages=[10        {"role": "system", "content": "You explain genai semantic conventions clearly."},11        {"role": "user", "content": f"What is genai semantic conventions?"},12    ],13    temperature=0,14)15print(response.choices[0].message.content)  # show output for debugging

• Skipping evaluation for GenAI Semantic Conventions before production
• No logging or tracing around otel genai steps
• Ignoring cost and latency implications

Quick recap — the most important points from this module.