Back to Prompt Library
testing

Simulate AI Application Impact Assessment

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Responsible AI Mental Health Impact Assessment

Format
Text-first
Lines
1
Sections
1
Linked challenge
Responsible AI Mental Health Impact Assessment

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Present your CrewAI team with a scenario: a new generative AI model capable of creating highly personalized, emotionally resonant video content for individual users. Task the team with generating an 'ImpactAssessmentReport' based on the 'ai_application_description' and 'focus_areas' provided in the sample input for the 'ImpactAssessmentReport' task. The report should detail potential mental health impacts, their mechanisms, and evidence, demonstrating advanced RAG and extended thinking.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the rubric, target behavior, and pass-fail criteria as the baseline for evaluation.

Tune next

Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.

Verify after

Make sure the prompt catches regressions instead of just mirroring the happy-path examples.