Build a repeatable workflow

Use this topic-specific sequence: brief → claims → draft → review → test → learn. 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 turn a verified meal-prep class brief into a truthful two-variant email test, begin with the job card and sanitized packet. Run the constrained prompt:

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.

Save the response beside its prompt and input version. Then apply the quality rubric and trace every factual phrase to the approved brief, check link and disclosure requirements, review accessibility and brand voice, then measure the predeclared conversion event. 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 fabricated urgency; fake statistics; multiple variables changed; vague CTA; stereotyped audience language; optimization without a hypothesis. 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 campaign evidence pack: source brief, claim ledger, variants, hypothesis, review sign-off, and measurement plan. Generation volume is not strategy. A useful campaign has a defensible promise, a specific audience action, and a test that can teach one thing. 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.