ChatGPT / Documents, Data & Research
ChatGPT: extract requirements without inventing acceptance criteria
Provide a specification with stable section labels. Decide whether recommendations and mandatory statements should be separated.
Environment and inputs: ChatGPT user guide · Feature and source access depend on the active account, app and organization settings. Optional file or app steps have a text-excerpt fallback. No fixed model version, price or usage quota is assumed.
What you will make
A practical ChatGPT guide to extract requirements without inventing acceptance criteria. Use the sample input and prompt, then check the result. Use a fictional small-office IT team as the practice setting. Keep the approved facts in a clearly labeled source block.
Prepare the source and scope
Provide a specification with stable section labels. Decide whether recommendations and mandatory statements should be separated. Open the ChatGPT app or website and start a focused conversation for this exercise.
Try this prompt
In ChatGPT, provide the prepared input, then send the following request. For real work, replace fictional details with approved facts.
Extract requirements into ID, Requirement, Source section and Testable evidence. Separate must from should. Mark an inferred test as Suggested, not part of the source.Review the result
Each mandatory statement should appear once and preserve its qualifiers and scope. Record each correction and its supporting source.
If the answer is wrong or incomplete
An assistant can turn an example into a requirement. Review modal verbs and check suggested tests with the product owner. For recurring work, keep the active source list with the project brief; for a one-off task, supply just the relevant excerpt.
Practice and completion check
Repeat with one incomplete input. Check the answer against the review criteria, remove unsupported claims and save the prompt with its source version. This workflow has not been verified in a customer deployment.