AIF-C01 - Prompt engineering and evaluation - Section 4.2
Evaluate and iterate on prompt quality.
Measure prompt quality against a rubric, compare variants, and iterate. Understand why a prompt that works on one example can fail on the next, and why evaluation sets matter.
Prompt evaluationEval setsIteration
More in this domain
Back to all Prompt engineering and evaluation objectives, or the AIF-C01 cert hub.
Examworthy is not affiliated with or endorsed by Amazon Web Services. Original, blueprint-aligned practice material only.