Back to Prompt Library
implementation

Claude Sonnet 4 for Personalization & Moderation Rules

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
For the 'Personalizer & Moderator' agent (using Claude Sonnet 4), define a set of instructions and rules for two primary functions: 1) adapting the summarizer's output to a given `user_profile` (e.g., adding technical jargon for 'Tech Enthusiast', simplifying for 'General Public'), and 2) moderating content for bias, sensationalism, or adherence to a journalistic tone. Provide a few examples of how Sonnet 4 would apply these rules.

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.