Skip to content
Nuvexa AI
Menu
Research · PRACTICAL TUTORIAL

Handle a requested metric when the evidence is absent

Refusing to invent a precise number preserves the meaning of verified data. An estimate needs visible assumptions and must not be labelled a fact.

Published by Nuvexa AI · Published · 2 min read

Start here

This example uses the sample details below. Replace them with your own facts before applying the instructions.

  • Public Etsy shop name supplied; private profit records unavailable.

Start with the facts

Public Etsy shop name supplied; private profit records unavailable. Keep the source, date and scope of each observation. A gap in the evidence is a question to investigate, not a fact to fill in.

Spot the problem

The wording or action to avoid is: “The shop earns exactly two thousand dollars weekly.” Refusing to invent a precise number preserves the meaning of verified data. An estimate needs visible assumptions and must not be labelled a fact.

Make the correction

Verified weekly profit cannot be determined from the supplied shop name. Use actual sales and expense records for that calculation.

Check before using the result

Check whether the requested metric is public, supplied or assumed before including any numerical output.

Worked example and reusable input

Use the stated inputs to reproduce checked local outputs. Replace sample facts when applying a brief to your own work.

TASK
Handle a requested metric when the evidence is absent

SAMPLE INPUT — replace with your actual facts
Public Etsy shop name supplied; private profit records unavailable.

AVOID
The shop earns exactly two thousand dollars weekly.

CORRECTED APPROACH
Verified weekly profit cannot be determined from the supplied shop name. Use actual sales and expense records for that calculation.

ACCEPTANCE CHECK
Check whether the requested metric is public, supplied or assumed before including any numerical output.

Key takeaways

  • Refusing to invent a precise number preserves the meaning of verified data. An estimate needs visible assumptions and must not be labelled a fact.
  • Check whether the requested metric is public, supplied or assumed before including any numerical output.