Back to Prompt Library
implementation

Leverage GPT-5 for Extended Thinking

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

Linked challenge: Multi-Agent Policy Impact Analysis

Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Agent Policy Impact Analysis

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Configure the `LegalInterpreter` agent to use GPT-5's extended thinking capabilities. When presented with ambiguous or complex policy language, instruct GPT-5 to perform multi-step reasoning: identify key terms, cross-reference with RAG-ed legal documents, consider precedents, and formulate a nuanced interpretation. Implement an adaptive reasoning budget based on the complexity of the legal text.

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.