Back to Prompt Library
testing
Full System Test with Diverse User Profiles
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: AI-Powered Personalized News Shorts Generator
Format
Text-first
Lines
1
Sections
1
Linked challenge
AI-Powered Personalized News Shorts Generator
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Implement the AutoGen agents and their interactions. Use a single news article (e.g., 'https://www.bbc.com/news/uk-politics-67252206') and run the `generate_news_short` task for at least two distinct `user_profile` inputs (e.g., one 'political analyst' interested in details, one 'casual reader' wanting a quick overview). Compare the outputs to assess personalization effectiveness and identify areas for refinement in agent prompts or interaction logic.
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.