Start with the job to be done

The working assignment is to investigate how later school start times affect teenagers without inventing evidence for a student writing a balanced evidence brief. That sentence is narrower than “use AI for research.” It identifies a deliverable and a reviewer. Write a definition of done with three layers: the output must satisfy the audience's need; factual or functional claims must be traceable; and a named person must own the final decision. 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.

Start by separating tasks. The model may draft, classify, transform, compare, or suggest. It may not silently approve, publish, grade, deploy, cite, or consent on someone's behalf. For this assignment the authoritative material is a bounded question, date range, source inclusion rules, search terms, labeled excerpts, and citation metadata. Anything absent from those inputs is either an explicit assumption or an unanswered question.

Use this prompt as a realistic starting contract:

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.

Notice what the prompt does: it states the setting, limits the output, names forbidden behavior, and requests evidence that can be reviewed. It does not ask the model to “make it amazing.” If a constraint matters, make it testable. Replace “be accurate” with a source boundary, formula check, test command, rights ledger, or approval step.

A useful response would look like this: A question bounded by population, intervention, outcomes, and time; search phrases include counterevidence and implementation costs; no fabricated bibliography appears. That description is intentionally observable. “Looks good” is not acceptance. The operator must open every source, check author/date/method, follow quotes to the original, compare primary findings with limitations, and label unsupported claims. Keep the source material beside the draft so review means comparison, not memory.

Run the work through scope → search → inspect → extract → synthesize → cite. Stop when an authoritative input is missing, a high-risk claim lacks evidence, private material cannot be safely removed, or the proposed action exceeds the permission granted. Escalation is successful workflow behavior, not model failure.

Common framing mistakes are invented citations; treating search snippets as evidence; collapsing correlation into causation; hiding disagreement; quoting a summary instead of the source. Prevent them by writing a one-paragraph job card: user, decision, deliverable, source of truth, constraints, reviewer, and stop condition. This card becomes the anchor for every later prompt.