Skip to content
ArchCrux

Interview Prep · Practice area

Evaluation and Quality

Choose evidence that shows a system works under the conditions that matter.

7 published questions

Question library

Choose a scenario

Agent task and trajectory outcomes

1 question available

Answerability, labels and datasets

1 question available

Experiments and causal evidence

2 questions available

Metric validity, judges and human signals

2 questions available

Statistical reliability

1 question available

7 questions available

Learn the systems behind these decisions in Topics.