Back to Prompt Library
testing

Execute End-to-End UGC Workflow & Evaluate Moderation

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
Run your complete LangGraph workflow from a user prompt through generation and moderation. Provide at least three distinct prompts, one of which is designed to intentionally violate a moderation rule. For each, submit the final generated content (or refined content after iteration) and the moderation report. Demonstrate how Guidance effectively prevented or flagged violations, and how iterative feedback improved compliant content.

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.