The team at the farm shop needs to promote its seasonal produce bundle, but the folder contains notes and no coherent asset set. The work must make sense to nearby families on a phone and lead naturally toward the choice to order a collection. The producer organizes the assignment around short-video scripting and uses a common buying hesitation as the first point of recognition.
A weak route would mention a common buying hesitation repeatedly without showing its effect on a real choice. Likely failure patterns are named in advance: invented features and unsupported performance claims. This affects production decisions, not merely the headline.
The center of the one-page brief is simple: help nearby families understand the seasonal produce bundle and decide whether to order a collection. Tone is fresh and straightforward. Required inputs are approved wording, timing, cost, eligibility, delivery method, and contact path; unsupported results and false urgency are prohibited. The sheet records capitalization, try-nanobanana prohibited language, claim sensitivity, reference rights, a 4:5 frame, phone-safe areas, a 22-second runtime, delivery formats, deadline, and reviewers. Confirmed facts, open questions, and illustrative examples occupy separate columns.
The planning sheet translates that search language into its underlying job: to evaluate unfamiliar image-making search language without implying endorsement. The acceptance test is a controlled test against one deliverable; speed alone is not an outcome. The phrase guides the job, but the seasonal produce bundle stays as the one illustrative case.
The 22-second vertical video answers one question: how the farm shop turns scattered notes for the seasonal produce bundle into an approved direction. Shot one gives a common buying hesitation three seconds, pairs voiceover with five words of human-set text, and shows the notes; the approved problem statement is its source. The next four seconds gather inputs, six compare hypothetical options, five show a reviewer correcting one flaw, and the final beat states the action. Each shot row keeps narration, screen copy, camera instruction, timing, evidence status, and reviewer distinct.
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 order a collection. If a fact is absent, the draft carries an editor query and stops short of publication wording. The copy earns space by helping the reader act, judge, compare, or avoid a known failure.
The visual is not decoration; it must explain a before-and-after choice without exaggeration within the seasonal produce bundle story. The prompt describes the seasonal produce bundle as subject, a foreground-to-background composition, one focal point, a restrained contextual background, deep green, warm gray, and off-white, soft directional light, and a 4:5 frame. Upper and lower safe zones remain quiet for human-added type, while the central action stays readable at phone width. ‘Room to Begin’ and ‘Weekend Window’ are hypothetical options for internal layout testing, not claims of availability or proof.
Core facts stay fixed, while opening, order, pace, composition, and interaction are rebuilt for each destination. A text-led post keeps the reasoning behind the seasonal produce bundle; an image-led post opens with the comparison and adds context in its caption; the carousel gives one decision to each card. Vertical video presents a common buying hesitation immediately and remains phone-safe. Long-form keeps the full comparison, while a community edit requests feedback before people order a collection.
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 seasonal produce bundle contains a master argument, a flexible visual frame, related caption copy, and a timed demonstration of the same decision. Approval happens before multiplication so a factual or visual mistake is corrected once rather than hunted across a folder of derivatives. The production board records the asset, audience purpose, supporting fact, destination format, approval state, reviewer, and how it helps people order a collection. The learning note defines one observable response, records date range and exposure, and avoids crediting a creative change for movement that the available evidence cannot explain. What the team learns is limited to this short-video scripting test; it does not become a guarantee, invented success story, or broad claim about every audience. Simple version discipline matters here: identify drafts by purpose, document the approved choice, and archive old exports away from publishable files before scheduling begins. Before scheduling, the producer checks the actual derivatives in their destination previews for compression, crop, caption placement, links, and any change to the intended reading order.
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. At full size and on a phone, visual review covers spelling, repeated letters, icons, hands, object count, edges, shadows, interface logic, stray marks, contrast, reading order, safe zones, and every crop from 4:5. 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. Sign-off follows when post, image, and clip agree on evidence, keep the fresh and straightforward manner, and direct nearby families honestly toward the choice to order a collection.
Specific model failures in this case include invented features and unsupported performance claims. Across formats, it can drift from the subject, produce malformed words and hands, invent controls, copy recognizable visual language, or report hypothetical outcomes as facts. A second reviewer compares each output with the source, inspects artwork at full size, and reads the script without prompt history.
The final folder separates the source sheet, approved route, editable copy, layered artwork, caption file, shot list, provenance notes, and export checklist. That record lets a solo operator revise one fact without regenerating every asset or guessing what was approved. The finished set stays modest: one approved idea, channel-specific expressions, and a documented human decision about the seasonal produce bundle.