Director Chair
All groups

A recreated video call: the client speaks first and names the problem, then the expert shares a screen and draws the system live, with speaker-labelled captions under it.

Presets

Mock client call

The viewer meets the problem as an overheard conversation before the solution is drawn.

Use when
System walkthroughs, consultation demos, case explainers, proposal videos.

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: Mock client call. The viewer meets the problem as an overheard conversation before the solution is drawn. How it works: A recreated video call: the client speaks first and names the problem, then the expert shares a screen and draws the system live, with speaker-labelled captions under it. Right for: System walkthroughs, consultation demos, case explainers, proposal videos. What we learned from tested runs: - The client speaks first, in her own words. - It explains a whole system but is not saved like a list: 2.8 percent of plays saved at 0.6 times the account's median. - A real client, a real person's face or a real vendor's logo needs written consent. 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
Length287.8 s
Aspect9:16
Visual changes per 10 s4.31 (mostly the captions)
Median segment1.9 s
First visual change1.57 s
First spoken word0.0 s
Spoken words per second2.88
Loudness, integrated-14.2 LUFS
True peak-1.4 dBTP
Sound floor-42.2 dBFS
Face in sampled frames61 percent, top third (two cartoon tiles)
Plays, saves3,445 plays, 2.8 percent saved (read 23 Oct 2026)
Against the account's median0.6 times

The recipe

  1. Recreate a call window in 9:16: a title bar with both names and a running timer, the active speaker's tile outlined, a toolbar at the bottom.
  2. Frame 0: the client's tile large, with a two-line title card naming the problem. The client says the first line.
  3. During the conversation keep two stacked tiles, client above and presenter below, about a third of the height each.
  4. When the presenter says they will draw it, switch to two small tiles on top and a shared drawing board below; draw each element stroke by stroke as it is named.
  5. Captions in a band under the screen with a speaker tag above each line.
  6. Keep real scene changes to about one every 6 to 8 seconds; the captions carry the faster rhythm.
  7. Close on the presenter's tile with the offer. Voice at -14 LUFS, no music under the dialogue.

Not for

Quick tips, anything under 90 seconds, product beauty, emotional stories, a real client without consent.

Related

Sources

Our own reading and measurement of a TikTok by @pro.glitch, posted 12 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.