Mastery: a verification routine

A sustainable verification routine is fast for low-risk work, rigorous for consequential work, and explicit about stopping. 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: create a quick claim-evidence scan; define escalation triggers for deeper review; save reliable sources and deterministic checks; track recurring errors and improve prompts and workflows. 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: A knowledge worker uses AI daily but checks facts only when an answer feels suspicious, allowing polished errors to pass unnoticed. 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].

• Relying on intuition to detect every hallucination. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
• Verifying forever without a decision threshold. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
• Keeping lessons private instead of improving shared procedures. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.

Turn Mastery: a verification routine 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: Mastery check.