A visual AI interface, shown through three real tasks
A founder-led launch film moves from a familiar interface problem to three escalating, side-by-side phone demos.
Field notes / why it works
The presenter names a familiar AI interface limitation by 0:15–0:33, then a second speaker explains the product premise before its 0:55 reveal. Three demos escalate from discovery at 1:02 to a customized recipe at 2:18 and multi-step planning at 2:46; 70 UI changes keep proof visible despite only 26 camera shots in 4:08.7.
Plate 01 / The format in one breath
A founder-like presenter describes a widely felt limitation in a familiar technology, a second technical voice explains the breakthrough, and the first speaker proves the claim through three increasingly involved phone tasks. The promise arrives at 0:15–0:33; the product itself appears around 0:55, with most of the runtime spent showing it respond.
Why it works
- The opening starts from shared experience, then turns it into a specific interface problem at 0:15–0:33; this gives the demo a reason to exist before the brand appears.
- A different speaker takes over from 0:20–0:49 to explain the engineering constraint, then hands back with a demonstration promise. The change of face and setting makes the claim feel more grounded.
- Only 25 cuts occur across 4:08.7, yet 70 changes within shots keep the demonstration moving. The phone examples grow from browsing (1:02) to a customized recipe (2:18) to multi-step trip planning (2:46).
Plate 02 / Format card
| Platform · aspect · length | X · 16:9, 1280×720 · 4:08.7 at 23.98 fps |
| Pace | 26 shots; 6.0–6.5 cuts/min allowing for two uncertain changes; 22.9 total picture changes/min; mean shot 9.57 s, median 4.31 s. Longest shot 55.39 s contains 21 UI changes. |
| Script | 618 transcribed words; 157 wpm across full runtime, about 217 wpm within voiced stretches; 46 sentences averaging 13.4 words; 4 questions. Some auto-transcribed product words are imperfect. |
| Voice | Two conversational adult male voices: measured, warm, credible; one presenter and one technical cofounder archetype. No voice imitation. |
| On screen | Roughly 60% seated presenter/phone UI demonstration, 12% bright-room technical interview, 24% purple-stage presenter, 4% black end card, estimated from shot spans. |
| Captions | No running subtitles. Small, restrained white interview lower third around 0:27–0:29; small labels within UI. |
| Sound | Nearly silent gaps under speech (−54.5 dBFS), so no continuous music bed; possible brisk instrumental outro in final ~10 s. No consistent cut accents. Measured −16.9 LUFS integrated, +0.2 dBFS true peak. |
| Structure | Shared problem → technical premise → three escalating demos → broad benefit → URL end card. Reveal at ~0:55; brand URL at 3:59. |
Pro / 13 plates + recipe
The first plates are open. The full dissection is Pro.
Get the timed shots, type and sound specs, and the runnable recipe.
Open the full blueprint- Plate 03 / The hook, frame by frame (first 3 seconds)Pro
- Plate 04 / Structure (beat sheet)Pro
- Plate 05 / Shot grammarPro
- Plate 06 / Visual style guidePro
- Plate 07 / Voice and deliveryPro
- Plate 08 / Sound designPro
- Plate 09 / PackagingPro
- Plate 10 / Script templatePro
- Plate 11 / Production planPro
- Plate 12 / PromptsPro
- Plate 13 / Edit recipePro
- Plate 14 / QA checklistPro
- Plate 15 / Make it yoursPro
- Recipe / runnable promptPro