Publication day is close, and the meal-prep service has only scattered notes for its rotating supper plan. The work must make sense to shift workers on a phone and lead naturally toward the choice to subscribe to the menu. The editorial angle is asset repurposing, with a mobile readability problem providing the opening tension.
The planning sheet translates that search language into its underlying job: to evaluate unfamiliar image-making search language without implying endorsement. Success means a controlled test against one deliverable, not a large gallery of attractive drafts. The phrase guides the job, but the rotating supper plan stays as the one illustrative case.
The first writing pass produces four message routes, not a pile of final captions. Four routes expose a mobile readability problem, show a three-step method, compare responsible choices, or document one decision at the meal-prep service. Selection follows the asset repurposing goal and rejects any route that needs a fabricated customer result.
The center of the one-page brief is simple: help shift workers understand the rotating supper plan and decide whether to subscribe to the menu. It sets the voice as helpful and realistic; requires approved offer wording, date, price, eligibility, fulfilment, and contact route; and bans invented scarcity, guarantees, and endorsements. Constraints specify spelling, mandatory and avoided terms, source permissions, the 1:1 ratio, safe zones, 22 seconds, file formats, responsible people, and release time. Three labels matter: confirmed, verify before use, and illustrative only.
One route branches into the explanatory post, short caption, hook, carousel sequence, spoken script, and title choices. The five cards move from audience problem to required facts, illustrative choice, human check, and the action to subscribe to the menu. A missing price, date, or eligibility detail becomes a question for the owner, never a confident sentence invented by the model. The copy earns space by helping the reader act, judge, compare, or avoid a known failure.
The 22-second vertical video answers one question: how the meal-prep service turns scattered notes for the rotating supper plan into an approved direction. Shot one gives a mobile readability problem three seconds, pairs voiceover with five words of human-set text, and shows the notes; the approved problem statement is its source. AI post generator collects inputs for four seconds; shot three shows the illustrative choice for six; shot four pauses on a human correction for five; shot five uses the remaining time for the approved next step. The shot sheet separates voiceover, on-screen text, direction, duration, source or assumption, and review note into six columns.
For the image route, the single job is to make the deadline legible without generated type. Prompt fields cover the rotating supper plan, spatial relationship, dominant focus, plain setting, the palette navy, pale blue, and restrained yellow, believable side light, and 1:1 output. Upper and lower safe zones remain quiet for human-added type, while the central action stays readable at phone width. 'Room to Begin' and 'Built for Tuesday' are hypothetical options for internal layout testing, not claims of availability or proof.
Generated material can fail through invented features and unsupported performance claims. A system may also change the subject between frames, deform text or interfaces, miss cultural meaning, imitate a familiar mark, or describe an example as a real result. A second reviewer compares each output with the source, inspects artwork at full size, and reads the script without prompt history.
The schedule also reserves enough time for correction, source checks, and another careful final reading before any finished asset is queued. The minimum viable set for the rotating supper plan contains a master argument, a flexible visual frame, related caption copy, and a timed demonstration of the same decision. Variants wait until the owner approves the chain; otherwise one unsupported assumption can spread through many exports and consume the review budget. A tracking row lists each asset, its purpose for shift workers, source fact, format, status, next reviewer, and relationship to the action to subscribe to the menu. After a small release, the owner compares observable signals chosen in advance, such as completed inquiries or saves, while keeping exposure and time period visible. The review can guide the next asset repurposing cycle while remaining explicit about uncertainty, sample limits, and other explanations for the observed response. The operator uses descriptive file names, records approval beside the source, and separates superseded exports from current work; this reduces the chance that a polished rejection reaches a scheduled post. Each exported derivative is opened in context before release, catching platform compression, unexpected cropping, unsafe captions, broken links, or a reordered message that the working file did not reveal.
Each channel receives a fresh edit of the approved argument rather than a resized duplicate. On a text feed, the producer explains the choice behind the rotating supper plan. An image feed foregrounds the visual task, while the carousel distributes the reasoning. A phone-first clip names a mobile readability problem within two seconds, a longer cut includes the review, and the community version asks for focused feedback tied to the choice to subscribe to the menu.
Human approval starts by matching every claim to confirmed inputs, checking current external rules against reliable sources, recording the access date, and testing audience fit and voice. Artwork is inspected at 100 percent and in place for text, symbols, hands, repeated objects, edges, light, interface plausibility, unintended marks, phone cropping, contrast, and reading order. A cold reviewer watches for changing objects, warped text, caption errors, unsafe margins, mispronunciation, uneven pace or audio, weak boundary frames, and lost meaning without sound. The owner approves only when every format preserves the facts, keeps the voice helpful and realistic, and gives shift workers a credible path to subscribe to the menu.
The delivery record shows the path from confirmed material through approved message, editable design, timed script, and final files. A late correction can flow through the set without forcing the owner to reconstruct which draft supplied a claim. The meal-prep service finishes with connected assets that can be checked and changed without pretending automation supplied judgment.