Back to Prompt Library
implementation

Develop Guidance-Powered Moderation Agent

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

Linked challenge: Craft Generative AI for User Generated Content

Format
Text-first
Lines
1
Sections
1
Linked challenge
Craft Generative AI for User Generated Content

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Develop the 'ModerationAgent' and integrate Guidance. This agent should receive multimodal content from the generator and apply a set of predefined Disney+ brand safety and content guidelines (e.g., 'no violence', 'age-appropriateness', 'only positive themes'). Use Guidance to both test generated content against these rules and, ideally, to constrain the generator if a violation is detected. Define how moderation feedback is sent back to the 'MultimodalGenerator' for refinement.

Adaptation plan

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

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.