Build a repeatable workflow

Use this topic-specific sequence: scope → search → inspect → extract → synthesize → cite. Give each stage one input, one output, and one gate. The first run should be narrow and reversible. Later automation is earned by measured reliability, not by how easy it is to connect tools.

For investigate how later school start times affect teenagers without inventing evidence, begin with the job card and sanitized packet. Run the constrained prompt:

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.

Save the response beside its prompt and input version. Then apply the quality rubric and open every source, check author/date/method, follow quotes to the original, compare primary findings with limitations, and label unsupported claims. A failed check returns to the smallest responsible stage; do not regenerate everything. If the source was missing, repair context. If the instruction was ambiguous, repair the prompt. If the candidate violates policy, stop and escalate rather than prompt around the policy.

Name an owner for source approval, generation, verification, and release. One person may hold several roles on a small project, but the role changes should remain visible. The reviewer needs the evidence packet, not merely the final artifact.

Define operational states: draft, needs evidence, blocked, approved, released, and rolled back. This vocabulary prevents a plausible draft from being mistaken for an approved result. Attach timeouts, retry limits, and an off switch to any automated stage.

Log the defect category rather than just “bad output.” This chapter's recurring defects are invented citations; treating search snippets as evidence; collapsing correlation into causation; hiding disagreement; quoting a summary instead of the source. Track their rate on representative cases. Review false positives and false negatives separately when classification is involved; track factual, continuity, or rights defects when producing media.

The end product is a research trail with question, query log, inclusion rules, source cards, claim-evidence matrix, and citation audit. 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. Periodically rerun a stable set of cases after changing models, prompts, source material, formulas, or settings.

Imagine the independent check fails after release. Identify how to stop distribution, identify affected outputs, restore the last approved version, notify the owner, and preserve enough evidence to learn. A workflow without rollback is only a happy-path demo.