Setting Goals and Success Criteria › Prioritizing Criteria
Michael BrenndoerferJuly 31, 20251 min read
AI Agent HandbookAll chapters Part 11 of 15Evaluation - Measuring Your Agent's Performance
Setting Goals and Success Criteria › Prioritizing CriteriaOne section · Sections in this chapter7 / 13 ↓
Sections in this chapter13
You probably can't optimize for everything at once. Some criteria will be more important than others.
For our assistant, we might prioritize like this:
- Safety (highest priority): The agent must never do something harmful or expose sensitive data.
- Correctness: The agent should get answers right. An agent that's fast but wrong isn't useful.
- Reliability: The agent should work consistently. Users won't trust an agent that's flaky.
- Efficiency: The agent should be reasonably fast, but we'd accept slower responses if it means higher correctness.
- User experience: Responses should be clear, but this is less critical than the above.
This hierarchy guides trade-offs. If improving speed reduces correctness, you don't do it. If making responses clearer adds a bit of latency, you might.
Your priorities will depend on your use case. A customer support agent might prioritize response time over exhaustive research. A medical diagnosis assistant should prioritize correctness above all else.