Checklist the per-video bar — engine/sim
82.3/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W42-Thu good|bad)⚠ 6 flag(s) — not yet ship-ready: copy_genericlow_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 · 28.6s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent shared field signature-3d | hook | 0–5.2s | kinetic-build | icon·liquid-chrome | ♪ node_lock | Vendors promise an AI that reads your CRM and tells you exactly who'll buy. on-screen: Vendors promise an AI that reads your CRM |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · mark · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape coneground redtreatment liquid-chromemotion kinetic-buildpower laser-lockinstrument laser-trace→"AI knows your customers" | |||||||
| 2 |  matches intent StackTrace template | diff | 5.2–13.0s | crossfade-8f | icon·white-knockout | ♪ node_lock | Real version: we feed the model your own win and loss history, and it shows the leads that look like past wins. on-screen: Reality: label, then learn |
expected on screen: red ground · a StackTrace panel over a dimmed Signal Field · Augur leads · code · crossfade-8f · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id StackTracevisual codeshape coneground redtreatment white-knockoutmotion crossfade-8fpower morphinstrument morph→Reality: label, then learncurate codeLines, errMsg, errType, fix, frames | |||||||
| 3 |  matches intent NumberedList template | teach | 13.0–18.6s | kinetic-build | icon·liquid-chrome | ♪ node_lock | The real cost of a model with no history is a sales team chasing leads that never close. on-screen: The cost: chasing ghosts |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape coneground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→The cost: chasing ghostscurate items, nodes | |||||||
| 4 |  first render · fix pending ComparisonTable templatedead_airgeneric_scene | proof | 18.6–23.6s | receipts-count | icon·white-knockout | ♪ node_lock | Minus the Hype |
expected on screen: red ground · a ComparisonTable panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ComparisonTablevisual receiptsshape coneground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate colA, colB, rows, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 23.6–28.6s | coalescence | icon·liquid-chrome | ♪ bed_out | Minus the Hype |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground redtreatment 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)
tiktokVendors promise an AI that reads your CRM and tells you who will buy. With no history, it cannot. We feed the model your own win and loss records through an Airtable MCP so it surfaces leads that look like past wins. (AI-assisted)
instagramThe pitch: an AI that knows who will buy.
The truth: a model with no history guesses.
Feed it your closed-won and closed-lost.
Let it surface leads that match past wins.
Label first. Then learn.
#AIsales #crm #leadscoring #automation #builtnotbought
linkedinVendors promise an AI that reads your CRM and tells you exactly who will buy. A model with no history of your wins and losses is just guessing, and your team ends up chasing leads that never close.
The real version: feed the model your actual closed-won and closed-lost records through an Airtable MCP. It surfaces the leads that look like your past wins.
The takeaway: label first, then let the model learn. History is the part the demo skips.
xVendors sell an AI that knows who will buy. With no history of your wins and losses, it guesses, and your team chases ghosts. Feed it your closed-won and closed-lost first. Method:
facebookVendors love to promise an AI that reads your CRM and tells you exactly who will buy. The catch: a model with no history of your wins and losses is just guessing.
The fix is simple. Feed it your real closed-won and closed-lost records, then let it surface leads that look like past wins. Start by exporting your win and loss history this week.
threadsVendors promise an AI that reads your CRM and tells you who will buy.
With no history, it guesses. Your team chases leads that never close.
Real version: feed it your closed-won and closed-lost first. Then it surfaces leads that match your past wins.
pinterestAI lead scoring that actually works: feed your model your real closed-won and closed-lost history first, then let it surface new leads that match past wins. CRM data labeling and lead prioritization method for sales teams.
blueskyVendors sell an AI that knows who will buy. With no history it just guesses, and your team chases ghosts. Feed it your real wins and losses first, then let it learn.
youtubeTitle: The AI That Knows Who Will Buy Is Guessing (Unless You Do This)
Vendors promise an AI that reads your CRM and predicts buyers. A model with no history of your wins and losses is guessing, and your team chases leads that never close. This short shows the real version: feed the model your closed-won and closed-lost through an Airtable MCP so it surfaces leads that match past wins. Label first, then learn. (AI-assisted)