Back to Prompt Library
planning|implementation

Claude Agent Core and Headline Generation

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

Linked challenge: Agentic News Headline Generator with Fact-Checking and Bias Detection

Format
Code-aware
Lines
1
Sections
1
Linked challenge
Agentic News Headline Generator with Fact-Checking and Bias Detection

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Initialize your Claude Agent using the Claude Agents SDK and the `claude-opus-4.1` model. Define the agent's primary role as a news editor. Implement a core function within your agent that takes a news article text as input and generates 3-5 distinct headline options. Focus on headlines that are concise, informative, and neutral in tone. Use Claude's capabilities for summarization and creative text generation. Provide the Python code for agent initialization and the headline generation step.

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 source structure until you know which part of the prompt is actually driving the result quality.

Tune next

Change domain facts, examples, and tool context first before you rewrite the instruction scaffold.

Verify after

Validate one failure mode at a time so prompt changes stay attributable instead of getting noisy.