Reasoning trace extractor prompt
By default most models give you a conclusion with no visible path to it. When the answer is wrong, you are left guessing whether the model misread the task, made a bad assumption, or fumbled a calculation. A reasoning trace fixes this: you instruct the model to write out its working in a clearly marked block before committing to a final answer. This tool wraps your existing prompt with those instructions so the logic is exposed, checkable, and easy to parse.
How it works
The tool keeps your task prompt intact and prepends a short instruction layer. That layer tells the model to first produce a reasoning block — in the tag style you chose — and only then produce the final answer in a separate, clean section. The depth setting controls how much the model elaborates: brief asks for a few decisive steps, while thorough asks it to surface assumptions, consider edge cases, and explain each inference. Because the output structure is fixed, you can reliably split the response into “reasoning” and “answer” downstream.
Tips and notes
- Parse on the tags. If you pick XML-style tags, extract everything between
<reasoning>and</reasoning>, then read the<answer>block as the user-facing result. - Use thorough depth for debugging. When you are trying to understand why a model keeps getting something wrong, thorough mode surfaces the faulty assumption far more often than brief mode.
- The trace is an argument, not a proof. A model can produce a clean-looking rationale that does not match how it actually arrived at the answer. Verify the steps, especially any numbers, rather than trusting them.
- Hide it from end users if you want. Log the reasoning for your own review and show users only the final answer block.