Evaluation
Category: Fundamentals“ee-val-yoo-AY-shun”
Testing an AI against known-good examples to measure how often it gets things right before you trust it.
Lesson #5: Trust, Risk & Running AI Responsibly →A road test before you hand someone the keys to the truck.
Asking a new AI ten questions you already know the answers to.
Running an estimator AI on 20 past jobs and comparing to the real invoices.
Scoring a support bot on 100 real tickets before letting it reply to customers.
Without evaluation you're guessing, and you won't notice when an update makes things worse.
Evaluation is scoring an AI on known answers before trusting it.
Build a 10-question test set for a task you'd hand to AI. Score it. Keep it for next time.
Hover or focus a choice to preview the new review date.
Exercises by category
- Agents0/21 · 0%
- Models0/10 · 0%
- Data0/11 · 0%
- Infrastructure0/22 · 0%
- Fundamentals0/15 · 0%
- NobleHub0/20 · 0%
Next badge: First Nail — 1 more exercise
Related terms
Picked automatically from the same category and the ideas this term shares.
Hand-picked pair
A standard test used to compare how well different AI models perform on the same task.
Hand-picked pair
When an AI confidently gives an answer that is simply made up.
Hand-picked pair
A setup where a person reviews or approves what the AI does before it counts as final.
Same category: Fundamentals
Adjusting an AI system so its answers become more accurate and reliable.
Same category: Fundamentals
How well an AI can show you the reasons behind an answer, in words a person can follow.
Same category: Fundamentals
Building and using AI in ways that are fair, honest, safe, and clearly accountable to real people.