Director Chair
All groups

Camera

Shot sizes 13Angles 13Camera moves 42Rigs 6Lenses 9Focus and depth 4

Frame

Composition 13Aspect ratios 6

Light and look

Light 11Time of day 4Colour looks 13Film stock and texture 9Art styles 6

People and places

Characters 5Expressions 31Settings 3

Motion

Subject motion and speed 8

Edit

Transitions 21Edit effects 41Sound 14

Story

Hooks 46Script arcs 10Video formats 11Calls to action 5Test and publish 16

Recipes

Presets 28Prompt guides 11

Tools

BoardModelsGuidesAboutAgent skill

The face only in the first six seconds with an audible before and after, then the product's own interface on black teaching one concept per beat, a numbered list filling slot by slot, the defined term coloured in the caption.

Presets

Interface as teacher

The viewer hears the promise in the hook, then learns one concept per beat from the product's own screens.

Use when
Product explainers and feature education for software with a visual interface.

Prompt instructions

You are my video producer. Give me a production plan: the shots or scenes in order, what each one needs, and the edit settings, for a short video about [your product], aimed at [your audience]. Technique: Interface as teacher. The viewer hears the promise in the hook, then learns one concept per beat from the product's own screens. How it works: The face only in the first six seconds with an audible before and after, then the product's own interface on black teaching one concept per beat, a numbered list filling slot by slot, the defined term coloured in the caption. Right for: Product explainers and feature education for software with a visual interface. What we learned from tested runs: - The face does not return after the hook, and no stock or generated imagery replaces the product's own interface. - Measured: 2.0 visual changes per 10 seconds and a median segment of 2.93 seconds, slow on purpose against 3.57 spoken words per second. - The reference runs at -18.7 LUFS; aim for -14. Be concrete: numbers, seconds and settings, no theory. Ask me one question first if something you need is missing.

Paste it into Claude, ChatGPT or Gemini.

Watch out

Notes

Measured on the reference

WhatValue
Length100.1 s
Aspect9:16
Visual changes per 10 s2.0
Median segment2.93 s
First visual change1.63 s
First spoken word0.0 s
Spoken words per second3.57
Loudness, integrated-18.7 LUFS
True peak-1.2 dBTP
Sound floor-34.4 dBFS (something under everything)
Face in sampled frames6 percent, top third
Plays, saves791,000 plays, 5.0 percent saved (read 22 Oct 2026)
Against the account's medianabout 50 times, measured on 13 Oct 2026

The recipe

  1. Hook, 0 to 6 seconds: the speaker in the top 45 percent, black below with an empty numbered list of the steps to come. The voice starts on frame 0 with the bare version of the thing, then the processed one.
  2. After 6 seconds the face is gone: full-frame black, the product's own interface components in a band across the middle of the frame, one concept per beat.
  3. Light the active component and dim the rest; fill one slot of the numbered list per step.
  4. Captions of about three words, white bold sans, sentence case, no box, under the interface, with the term being defined in the accent colour.
  5. Hold each visual 2.5 to 3.5 seconds while the voice runs at about 3.5 words per second.
  6. Close on the full list and name the product once.

Not for

Products without a visual interface, testimonials, emotional stories, anything under 30 seconds.

Related

The speaker fills the top 45 percent for the first six seconds, then the face is gone and the product's interface carries the rest.

Face only in the hookPrompt

She says this mic has nothing on it, and in the middle of the sentence the sound changes to the processed version; below her, six empty numbered slots wait.

The result in the hookPrompt

Captions of about three words in white, the term being defined in the brand accent colour at the moment it is said.

Coloured keyword in the captionPrompt

A card with a question as its title, a one-sentence answer, and the address of the learn page in small type.

Definition cardPrompt

The face in the hook and at the end, the product's own interface teaching one concept per beat in between, definitions as cards.

The interface carries itPrompt

Run the voice through a high-pass at 100 Hz, a downward expander, a de-esser, a 3 dB lift around 3.5 kHz, a compressor and a limiter, in that order.

Six-stage voice chainPrompt

Sources

Our own reading and measurement of a TikTok by @thefranswah, posted 8 Oct 2026. The clip is a third-party reference and is not shown; the words here are ours Source Checked 2026-11-13.

For agents: this card as markdown, as JSON.