Set a quality and verification bar

For turn a verified meal-prep class brief into a truthful two-variant email test, 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 busy beginners considering a local class can take the intended action. Safety includes the boundary that you must never paste customer lists, personal profiles, unpublished campaign data, or sensitive targeting attributes into an unapproved model. 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 trace every factual phrase to the approved brief, check link and disclosure requirements, review accessibility and brand voice, then measure the predeclared conversion event. The expected candidate is Two compact emails with the same offer and CTA; each claim maps to the brief, while the changed angle is explicitly labeled as the sole test variable. 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.

Use only these facts: two-hour in-person class; ingredients included; participants leave with five recipes. Audience: busy cooking beginners. Draft a subject line and email under 140 words with one sign-up CTA. Do not claim savings, health outcomes, superiority, scarcity, or testimonials. Then make variant B by changing only the angle from convenience to confidence.

After generation, sample beyond the happy path. Failures such as fabricated urgency; fake statistics; multiple variables changed; vague CTA; stereotyped audience language; optimization without a hypothesis 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. Generation volume is not strategy. A useful campaign has a defensible promise, a specific audience action, and a test that can teach one thing. Quality assurance is part of the work, not an apology added at the end.