Worked example: verify an answer

A visible verification log makes it possible to revise only the claims that fail and preserve supported work. This principle matters because an AI system produces likely output from the context and instructions it receives; it does not automatically know the organization’s current facts, private policy, unstated intent, or acceptable risk.

Use the following sequence for this page: extract each eligibility, deadline, and funding claim; find the current official program page and guidance; compare wording, dates, and definitions; rewrite with citations, uncertainty, and a human confirmation step. The sequence is a guide, not a ritual. Skip a step only when its question truly has no effect on the outcome, and strengthen it when mistakes would be costly.

Return to the opening case: An AI answer claims a grant closes Friday, requires five years of trading history, and covers 60 percent of project cost. Begin by rewriting the request as a small contract. Name the intended reader or user, the authoritative material, the operation to perform, the required output, and the review owner. If current information is required, identify where it will come from. If exact calculation or action is required, assign that step to a deterministic tool or an approved system rather than relying on prose generation.

A useful instruction could follow this shape:

Goal: help [reader] accomplish [outcome]. Use only [named sources or supplied material] for factual claims. Perform [specific operation] and return [format]. Mark missing information as TBD or ask a focused question; do not guess. Before the result is used, [named person or role] will check [criteria].

• Quietly correcting the answer without recording why. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
• Using an archived page as current authority. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
• Turning an ambiguous requirement into a definite yes or no. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.

Turn Worked example: verify an answer into a template you can reuse this week: job statement, required evidence, failure mode to catch, and reviewer. Store it next to your other spot wrong answers notes. When the job changes, rewrite only the job statement and re-run the same failure-mode list — do not invent a new workflow from scratch. Role of this page: Worked example.