Lesson 6 of 8 · Build AI Apps with Real APIs
In this lesson. Add logging, eval hooks, and an owner before you call it shipped.
What you will learn
- Logs you can debug from
- A small eval set on the critical path
- Alerts for errors, cost, and latency
Walkthrough
Demos rot. This lesson adds the production minimum: structured logs, a tiny eval set, and a named owner for the prompt. You will also list the first three alerts you would want (error rate, cost spike, latency). That is how an API feature survives the second month.
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 Build AI Apps with Real APIs 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
Write a one-page runbook for your chat slice: logs, evals, and who gets paged.
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 “Logs you can debug from” 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.