Uncertainty and high-stakes answers

Verification depth should rise with harm, irreversibility, novelty, and the difficulty of detecting an error. 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: identify the decision and potential harm; recognize when qualified human review is required; ask for assumptions and bounded uncertainty; avoid acting on incomplete personalized guidance. 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 user receives AI guidance touching medication, employment eligibility, and a financial deadline, all stated without jurisdiction or personal context. 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].

• Using disclaimers as a substitute for safe behavior. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
• Requesting false numerical confidence. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
• Sharing sensitive records to obtain a more tailored guess. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.

Turn Uncertainty and high-stakes answers 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: Safety and governance.