Work a full example

The project is to design a small email campaign with a claim ledger, two controlled variants, approval record, and results template. The user is busy beginners considering a local class. Definition of done: the intended action is clear, the candidate uses approved evidence, blocking safety checks pass, and another person can reproduce the key result.

Stage 1: prepare

Create the job card and collect approved product facts, audience problem, channel, word limit, brand voice, prohibited claims, CTA, and test hypothesis. Remove or replace prohibited material: never paste customer lists, personal profiles, unpublished campaign data, or sensitive targeting attributes into an unapproved model. Add one ordinary case, one boundary case, and one hostile or misleading case. Record unknowns instead of filling them with plausible guesses.

Stage 2: draft

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.

The first candidate should be 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. In this worked run, imagine it also exhibits one realistic defect from this set: fabricated urgency; fake statistics; multiple variables changed; vague CTA; stereotyped audience language; optimization without a hypothesis. Do not hide the defect. Mark the exact criterion it violates and decide whether the cause belongs to context, instruction, model capability, or the surrounding process.

Stage 3: repair narrowly

Issue a targeted revision:

Revise only the failed criterion identified below.
Preserve all verified content and the original output contract.
Do not add facts or assets.
Return the corrected artifact plus a one-line change note.
Failed criterion: [paste criterion and evidence]

A narrow repair keeps the review surface understandable. If the model cannot repair without new authoritative information, pause and obtain that information.

Stage 4: verify and release

Now trace every factual phrase to the approved brief, check link and disclosure requirements, review accessibility and brand voice, then measure the predeclared conversion event. Record pass/fail evidence for each criterion and have the named reviewer make the release decision. Generation volume is not strategy. A useful campaign has a defensible promise, a specific audience action, and a test that can teach one thing. Save limitations in language the audience can understand.

The durable deliverable is not only the final result. It is a campaign evidence pack: source brief, claim ledger, variants, hypothesis, review sign-off, and measurement plan. Write what surprised you, which check found it, what you changed, and which control should become the default. A clean retrospective distinguishes a prompt improvement from a data, tool, or policy change.