Lesson 2 of 10 · Computer Vision for Builders, Not Researchers
In this lesson. When a detector is enough, when you need a VLM.
What you will learn
- Detectors
- VLMs
- Cost latency
Walkthrough
You will choose. Counting widgets might be a detector. Open-ended “what’s wrong” might be a VLM. Cost and latency follow the choice.
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 Computer Vision for Builders, Not Researchers 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
Choose a stack for your contract and say why the other is worse.
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 “Detectors” 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.