PROMPT
# Food Video: food scene 185 AOV Growth Strategy for increase AOV $68 to $129 - slow push-i - Legal Tech
## EXPERT ROLE
Act as a senior Food specialist. Solve the exact task. Use supplied scenario details as inputs, separate facts from assumptions, and avoid generic advice.
## INTENT
**Job:** Improve the named business/performance outcome using a measurable, testable intervention.
**Audience:** Professionals or practitioners using AI for food tasks.
**Context:** Primary video platform/application
**Success:** define 2–4 observable criteria tied to the requested outcome.
## WORKING BRIEF
Treat this as the authoritative source brief. Preserve useful specifics; do not invent facts or turn scenario values into verified claims.
> PROMPT FOR RUNWAY GEN-4 TURBO / SORA / LUMA: Scene: food scene 185 - increase AOV $68 to $129 - slow push-in - photorealistic 8K - variant 2410, Food premium commercial for Legal Tech, photorealistic not CGI, Arri Alexa 65, golden hour environment, action rank #1 for 20 keywords, mood bright optimistic Camera: slow push-in 24fps 85mm f/2.8, focus pull at 2s Lighting: cinematic three-point large soft 12x12 diffusion 5600K + fill + rim kicker, volumetric haze, global illumination Duration: 8s 24fps 180° shutter, 3840x2160, 16:9 master + 9:16 vertical centered + 1:1 safe SHOT LIST: 0-2s establishing wide breathing, 2-4s reveal move start subject enters light shift focus pull, 4-6s hero macro detail thumbnail hold 1.5s, 6-8s outro pull back 20% headroom logo CTA clean freeze Negative: no morphing, no extra limbs, no text watermark, no flicker jitter, no AI wobble, no low-res blurry Audio: luxury tick 60bpm QA: Loop clean? Headroom? Flicker? Apple approved?
## CATEGORY-NATIVE PRODUCTION
Intent → Story/Action Strategy → Shot & Motion Design → Model Adapter → Failure Prevention → Variant Test → Platform Adaptation → QA. Translate the brief into production-ready instructions. Lock the subject/identity first, then define the dominant visual idea, focal hierarchy, composition, viewpoint or shot design, environment/context, lighting, material or surface behavior, depth/scale, typography or copy-safe zones when relevant, aspect ratio and crop. Preserve all supplied reference invariants. For video, also define shot duration, action beats, camera movement, continuity anchors and transition logic. Do not add technical vocabulary that does not improve the specific asset.
## MODEL ADAPTER
Adapt the production prompt to the requested model(s). Use precise semantic instructions for general models; use model-specific syntax only when supported. Never invent parameters or capabilities. If multiple models are listed, preserve the same creative intent while translating only the syntax/control layer.
## FAILURE PREVENTION
Address only relevant risks: identity drift across frames; temporal inconsistency or continuity breaks; unnatural motion/camera behavior; timing that weakens the story; platform-safe framing failure. For each selected risk, state the prevention rule and the visible QA signal that proves it is controlled. Treat supplied logos, text, faces, products, proportions and other identity-critical references as invariants.
## VARIANT + PLATFORM TEST
Create up to three controlled variants only when useful: A changes composition, B changes one treatment variable, C changes context/crop/platform presentation. Preserve identity and strategic intent. For each variant state the hypothesis, variable, success signal and decision. Adapt crop, safe areas, viewing distance, text density and hierarchy to the actual platform without changing the core concept.
## PROFESSIONAL HANDOFF
Return the final generation-ready prompt plus the key inputs, locked invariants, negative/failure-prevention rules, target aspect ratio, platform adaptation and QA checklist. Make the result usable by a designer, art director, marketer or production team without needing to reconstruct missing decisions.
## QA
Check intent, category-native quality, identity/reference integrity, composition, technical coherence, temporal continuity for video, platform fit, text/logo fidelity where relevant, failure prevention and professional usability. If a critical gate fails, make the smallest responsible correction and rerun the relevant check.
## OUTPUT CONTRACT
Return a specific, immediately usable result. Include assumptions only when material; use concrete decisions and examples where useful; omit irrelevant boilerplate. Do not merely restate this prompt.
## SPECIALIST STANDARD
Judge the result using the professional standards of **Food**. Replace generic quality language with observable category-specific criteria.
## MODEL-NEUTRALITY
Keep core reasoning model-agnostic unless model-specific behavior materially changes the result. When a model is specified, adapt only the relevant syntax or capability.
## DELIVERY FIT
Optimize the final artifact for **Primary video platform/application** only where platform behavior changes the format, attention pattern, constraints, or delivery.
## UNIQUENESS CHECK
Before finalizing, state why this prompt is materially different from nearby prompts: different intent, strategy, use case, audience, output, or decision—not merely different wording.