Writing clear specifications
Listen to this lesson
Nigerian voice narration
Fictional training case. A department requested 'good chairs' with no further detail, leaving the procurement unit unable to issue a fair RFQ. Vague requests invite inflated or inconsistent vendor quotes, so the request must be converted into measurable, brand-neutral specifications before it goes out to bid. Work through the example, identify the evidence needed and practise the method with cleared or synthetic inputs. Any additional figures in the explanation are separate practice examples, not claimed rows in a downloadable file.
Worked example
Ask AI to turn the vague request into measurable specifications: seat dimensions, frame material, load rating in kilograms, warranty period, and delivery location — each a number or a checkable fact, not an adjective. Review the draft for any brand names that crept in (a common AI habit when it recognises a product category) and replace them with 'or equivalent' wording to preserve open competition. Confirm the load rating and materials match what the requesting department actually needs — AI may propose office-standard specs that don't match, for example, a reception area needing heavier-duty seating. Circulate the finalised spec sheet for RFQ issuance.
The method
Adjective-to-number conversion: for every vague word in the original request (good, strong, nice), demand a measurable substitute (load rating ≥120kg, 5-year warranty) so vendors are quoting against the same verifiable standard rather than their own interpretation.
Worked practice and common mistakes
Specify how a requirement will be checked at delivery. A 120kg load rating needs appropriate evidence, not merely the word “strong.” Prefer brand-neutral performance measures; adding “or equivalent” alone does not cure requirements tailored to one product. Confirm dimensions, warranty and use case with the requesting unit instead of relying on a generated office-standard default.
Review before using the result
Scan the spec sheet for brand names and vague adjectives one more time before release, and confirm the load rating matches the actual use case of the requesting department.
Your workplace practice
Use the recommended free assistant with this lesson's fictional example. Ask for the output described in the worked example. Keep a copy of the input and draft. Compare the result with the verification steps above, record any correction, and retain placeholders where evidence is missing. The expected result is a checked draft for human review, not an automatically approved decision. Course examples and practice responses are fictional; amounts, dates, rules and thresholds are not official guidance or supplier quotations.
Why this tool: Turns vague needs into measurable specs with good follow-up questions.
Hit a free limit? Switch to ChatGPT or Gemini and continue — the prompt works in any assistant.