Lesson 3 of 10 · Deploy LLMs in Production Without Chaos
In this lesson. Request id, token counts, model, prompt version.
What you will learn
- Request id
- Tokens and model
- Prompt version
Walkthrough
You will log enough to debug a bad answer without logging secrets. Token counts are cost. Prompt version is how you correlate evals. This is the telemetry spec.
Work through the ideas in order. After each point, pause and connect it to a task you already do — a document, a workflow, or a feature you own. The goal of Deploy LLMs in Production Without Chaos is usable skill, not a pile of notes.
If something is unclear, rewrite it in your own words before you continue. Teaching the step back to yourself is the fastest way to see gaps.
Practice
List the log fields for one call.
Keep the first attempt small. A finished example you can reuse beats a perfect plan you never run.
Check your understanding
- Can you explain the goal of this lesson in one sentence to a teammate?
- Where would you apply “Request id” in your own work this week?
- What would you change on a second pass of the practice?
Next. Continue to the following lesson when the practice has a real artifact, even a rough one.