Checklist the per-video bar — engine/sim
80.8/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W35-Thu good|bad)⚠ 6 flag(s) — not yet ship-ready: low_vo_coveragedead_airgeneric_scene · see docs/strategy/VIDEO-CHECKLIST.md
Composition comp · template family · expected output
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 5 scenes · 28.5s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  first render · fix pending shared field signature-3ddead_air | hook | 0–5.0s | kinetic-build | icon·liquid-chrome | ♪ node_lock | AI will tell you what customers want, they say, as if it can read minds it never met. on-screen: "AI does customer research" |
expected on screen: black ground · icosa hero in the shared Signal Field · Signum leads · mark · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape icosaground blacktreatment liquid-chromemotion kinetic-buildpower laser-lockinstrument laser-trace→"AI does customer research" | |||||||
| 2 |  matches intent StackTrace template | diff | 5.0–12.6s | crossfade-8f | icon·ember-fill | ♪ node_lock | What works: record real customer calls, transcribe them with Whisper, and let the model cluster the actual quotes. on-screen: Transcribe, then cluster |
expected on screen: black ground · a StackTrace panel over a dimmed Signal Field · Signum leads · code · crossfade-8f · icon·ember-fill logo · caption bottom-left spec (the prompt): comp_id StackTracevisual codeshape icosaground blacktreatment ember-fillmotion crossfade-8fpower morphinstrument morph→Transcribe, then clustercurate codeLines, errMsg, errType, fix, frames | |||||||
| 3 |  matches intent NumberedList template | teach | 12.6–18.5s | kinetic-build | icon·wireframe | ♪ node_lock | The cost is you still have to talk to humans. Record and transcribe your next three customer calls. on-screen: The cost: real conversations |
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape icosaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→The cost: real conversationscurate items, nodes | |||||||
| 4 |  first render · fix pending RankList templatedead_airgeneric_scene | proof | 18.5–23.5s | receipts-count | icon·white-knockout | ♪ node_lock | Minus the Hype |
expected on screen: black ground · a RankList panel over a dimmed Signal Field · Signum leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape icosaground blacktreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate rows, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 23.5–28.5s | coalescence | icon·liquid-chrome | ♪ bed_out | Minus the Hype |
expected on screen: black ground · icosa hero in the shared Signal Field · Signum leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape icosaground blacktreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Minus the Hype | |||||||
Format stack 3 aspects · same scenes[], re-cropped
9:16
1080×1920
Stories · TikTok · YouTube Shorts · Reels
1:1
1080×1080
LinkedIn · Facebook · Instagram
16:9
1920×1080
X/Twitter · YouTube · LinkedIn video
Channels 9 destinations
LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBluesky
Social captions supplemental published copy · per channel (comp_id level)
tiktok"AI does your customer research" they say. What works: record real customer calls, transcribe them with Whisper, then let the model cluster the actual quotes. The cost: you still have to talk to humans. (AI-assisted)
instagram"AI does customer research"
Not from thin air it doesn't.
Record the calls.
Transcribe with Whisper.
Let the model cluster real quotes.
The cost: you still talk to humans.
#customerresearch #ai #whisper #productmarketing #voiceofcustomer
linkedin"AI will tell you what customers want" is the pitch. It can't invent what your customers said, it can only organize it.
What works: record real customer calls, transcribe them with Whisper, and let the model cluster the actual quotes into themes. The insight comes from the words they used, not a guess.
The honest cost: you still have to talk to humans. Record and transcribe your next three customer calls.
x"AI does customer research" can't invent what customers said. Record real calls, transcribe with Whisper, let the model cluster the actual quotes. The cost: you still have to talk to humans. temerarii.xyz/build
facebook"AI does your customer research" sounds nice, but it can't tell you what it never heard. What works: record real customer calls, transcribe them with Whisper, and let the model cluster the actual quotes into themes. The catch is you still have to talk to humans. Record and transcribe your next three calls.
threads"AI does customer research" they say. It can't invent what your customers told you.
Record real calls, transcribe with Whisper, let the model cluster the actual quotes. The cost is the part nobody likes: you still have to talk to humans.
pinterestHow to do real customer research with AI. The method: record actual customer calls, transcribe them with Whisper, then let the model cluster the real quotes into themes. AI organizes what customers said, it can't invent it. The honest cost is you still have to talk to humans. Voice of customer research method for marketers.
bluesky"AI does customer research" can't invent what customers said. Record real calls, transcribe with Whisper, let the model cluster the actual quotes. The cost: you still have to talk to humans.
youtubeTitle: AI Customer Research, Minus the Hype (Transcribe, Then Cluster)
"AI will tell you what customers want" is the promise, but it can't invent what it never heard. The method that works: record real customer calls, transcribe them with Whisper, and let the model cluster the actual quotes into themes. The insight lives in the words your customers used. The honest cost: you still have to talk to humans. Record and transcribe your next three calls.