Lesson 1 of 8 · Build AI Apps with Real APIs
In this lesson. Match chat, embeddings, and vision APIs to the product job.
What you will learn
- Chat versus embeddings versus multimodal
- Latency, cost, and context as design inputs
- A decision table for one feature
Walkthrough
APIs are not interchangeable. Chat endpoints draft and decide, embeddings retrieve, vision reads images, and speech handles audio. This lesson maps each to a product job and names the constraints that should drive the choice: latency, cost, context length, and structured output. You will leave with a decision table, not a brand preference.
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
Pick one feature you want to ship and write which endpoint it needs and why the others are a poor fit.
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 “Chat versus embeddings versus multimodal” 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.