Back to Prompt Library
implementation

Claude Opus 4.1 Prompt for Structured Extraction

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

Linked challenge: Financial Proxy Analyst AI

Format
Text-first
Lines
1
Sections
1
Linked challenge
Financial Proxy Analyst AI

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Design a system prompt for Claude Opus 4.1 to extract specific entities (e.g., 'CEO_Compensation_Total', 'Board_Diversity_Metrics', 'Shareholder_Proposal_Summary') from a provided text chunk of a proxy statement. The output should be a JSON object. Ensure the prompt explicitly instructs the LLM on handling missing data and ambiguous phrases, and include examples.

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.