10 scenarios, graded as you go, with the exact grading principle for every answer. Start free, no sign-up.
Sample scenarios
In prompt-writing tasks where your goal is to 'stump the model' (induce a realistic failure), which prompt is strongest?
'Tell me about World War II.'
A realistic multi-constraint prompt combining a specific role, a negative constraint, an exact output schema, and a subtle false premise or source-only rule.
'Write a 10,000-word essay using no vowels.'
'What is 2 + 2?'
Show the answer
B. A realistic multi-constraint prompt combining a specific role, a negative constraint, an exact output schema, and a subtle false premise or source-only rule.
Silly impossible constraints ('no vowels') are rejected by QA reviewers as unnatural. Strong adversarial prompts look like real user tasks that layer multiple realistic constraints or tricky edge cases.
A prompt says: 'Using ONLY the attached lease excerpt, state the late fee.' The attached excerpt says nothing about a late fee. Model A says '$50 (standard)'. Model B says 'The provided excerpt does not mention a late fee.' Which model passes?
Model A, because $50 is common.
Model B, because strict groundedness requires acknowledging missing information rather than guessing from outside knowledge.
Both fail.
Model A, because it is more decisive.
Show the answer
B. Model B, because strict groundedness requires acknowledging missing information rather than guessing from outside knowledge.
When a prompt restricts the model to provided context, inventing an unstated fact—even a plausible one—is a groundedness failure.
Principle: Groundedness: Abstaining on Missing Context
Why do platforms reject prompts that contain 'contradictory constraints' (e.g., 'Write a 500-word summary in exactly 10 words')?
Because an impossible prompt makes it impossible for any model to succeed, invalidating the evaluation.
Because 500 words is too long.
Because summaries cannot be 10 words.
They don't—contradictory constraints are encouraged.
Show the answer
A. Because an impossible prompt makes it impossible for any model to succeed, invalidating the evaluation.
Adversarial prompts must be *solvable* by a careful model. Contradictory instructions create an ungradable, unfair test.