AI Quality · Picture Book
What Are LLM Evaluations?
An eval is an obstacle course for an AI.
1. A nice answer can still be wrong
The AI says, “Your refund is done,” but the money never moved.
2. Build a small obstacle course
Give the AI real tasks, awkward edge cases, broken tools, and trick questions.
3. Check the finish line, not the speech
A grader checks the real outcome, the path taken, and whether any safety rule broke.
4. Every real failure becomes a new cone
Fix the problem, add it to the course, and run the course whenever the agent changes.
Longer version: LLM Evaluations reference entry
Sources: Anthropic, “Demystifying evals for AI agents”; NIST AI 600-1.