Set a quality and verification bar

For investigate how later school start times affect teenagers without inventing evidence, define quality across accuracy, completeness, usefulness, safety, and reproducibility. Weight dimensions according to harm. A cosmetic miss can be revised; an unsupported claim, broken calculation, privacy leak, or rights violation blocks release.

Translate each dimension into observable checks. Accuracy means a claim, value, behavior, or frame agrees with an authoritative source. Completeness means every required field or stage appears. Usefulness means a student writing a balanced evidence brief can take the intended action. Safety includes the boundary that you must share only excerpts you are permitted to process; remove participant identifiers, unpublished interview material, paywalled full text, and confidential research data. Reproducibility means the prompt, input version, settings, and review evidence are saved.

Use checks from cheapest to strongest:

1. Contract check: required sections, schema, length, and prohibited content.
2. Source check: trace claims and values to supplied evidence.
3. Edge check: run normal, boundary, missing, and adversarial cases.
4. Independent check: calculate, test, rehearse, listen, inspect, or open the original.
5. Human gate: a responsible reviewer approves consequential use.

In this chapter, the concrete verification is to open every source, check author/date/method, follow quotes to the original, compare primary findings with limitations, and label unsupported claims. The expected candidate is A question bounded by population, intervention, outcomes, and time; search phrases include counterevidence and implementation costs; no fabricated bibliography appears. Record actual evidence, not a checkbox copied from the prompt.

Score each criterion 0 (fails), 1 (partly), or 2 (passes). Any zero for factual correctness, permission, privacy, or required disclosure is an automatic stop. A total score is useful for comparing iterations, but it must never average away a blocking defect.

Topic: effects of later secondary-school start times on adolescent sleep and attendance. Propose one focused question, five search phrases including a skeptical angle, and inclusion/exclusion rules. Do not provide citations. Mark every factual statement that will require a source.

After generation, sample beyond the happy path. Failures such as invented citations; treating search snippets as evidence; collapsing correlation into causation; hiding disagreement; quoting a summary instead of the source often survive a superficial review because the output has the right shape. Use a counterexample designed to expose the riskiest assumption.

Store the rubric result, reviewer, date, input version, failed cases, and unresolved limitations. If the artifact changes, rerun affected checks. AI can map a search and organize supplied evidence; it is not the evidence. The non-negotiable habit is opening and judging the original source. Quality assurance is part of the work, not an apology added at the end.