Back to Prompt Library
implementation

OpenAI o3 Prompt for Multimodal Summarization

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
Craft a detailed prompt for the 'Content Summarizer' agent (using OpenAI o3) that takes a news article (URL/text) and aims to produce a concise summary. The prompt should instruct o3 to identify key entities, extract the core narrative, and generate a summary suitable for a vertical short-form video script. Emphasize multimodal understanding hints if applicable (e.g., 'Focus on the visualizable aspects mentioned').

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.