Checklist the per-video bar — engine/sim
81.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W41-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 · 26.4s · 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 | The promise: snap a receipt, AI categorizes everything, taxes done. on-screen: "AI does your bookkeeping" |
expected on screen: black ground · box hero in the shared Signal Field · Faber leads · mark · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape boxground blacktreatment liquid-chromemotion kinetic-buildpower laser-lockinstrument laser-trace→"AI does your bookkeeping" | |||||||
| 2 |  matches intent LogStream template | diff | 5.2–11.100000000000001s | crossfade-8f | icon·ember-fill | ♪ node_lock | Here's the honest version. The model reads the receipt and pulls fields into a structured row. on-screen: Reality: extract, never decide |
expected on screen: black ground · a LogStream panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·ember-fill logo · caption bottom-left spec (the prompt): comp_id LogStreamvisual codeshape boxground blacktreatment ember-fillmotion crossfade-8fpower morphinstrument morph→Reality: extract, never decidecurate codeLines, rows | |||||||
| 3 |  matches intent NumberedList template | teach | 11.1–16.4s | kinetic-build | icon·wireframe | ♪ node_lock | Let AI judge your money and you get a ledger you can't defend to anyone. on-screen: The cost: numbers you can't defend |
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→The cost: numbers you can't defendcurate items, nodes | |||||||
| 4 |  first render · fix pending RankList templatedead_airgeneric_scene | proof | 16.4–21.4s | receipts-count | icon·white-knockout | ♪ node_lock | Minus the Hype |
expected on screen: black ground · a RankList panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape boxground blacktreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate rows, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 21.4–26.4s | coalescence | icon·liquid-chrome | ♪ bed_out | Minus the Hype |
expected on screen: black ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground 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 bookkeeping." The promise: snap a receipt, taxes done. Honest version: the model reads the receipt and pulls the fields into a row. It extracts. You decide. (AI-assisted)
instagram"AI does your bookkeeping."
Reality:
The model reads the receipt.
It pulls fields into a row.
It extracts. You decide.
Let AI judge your money and you get a ledger you cannot defend.
#bookkeeping #aitools #smallbusiness #minusthehype #buildinpublic
linkedin"AI does your bookkeeping" is a tidy promise: snap a receipt, AI categorizes everything, taxes done.
Here is the honest version. The model is good at one job: read the receipt and pull the fields into a structured row. Date, vendor, amount. That is extraction, and it is genuinely useful.
What it should not do is decide. The moment you let AI judge what counts and how to book it, you get numbers you cannot defend to an accountant or an auditor. Let the model extract. Keep the judgment yours.
x"AI does your bookkeeping." Honest version: the model reads the receipt and pulls fields into a row. It extracts, you decide. temerarii.xyz
facebookThe promise is clean: snap a receipt and AI does your taxes. Here is the honest version. The model reads the receipt and pulls the fields into a row. That part is useful. But let it decide how to book things and you end up with numbers you cannot defend. Let AI extract, and keep the judgment yours. More at temerarii.xyz.
threads"AI does your bookkeeping."
Honest version: the model reads the receipt and pulls fields into a row. That is extraction, and it helps. Let it decide how to book things and you get numbers you cannot defend. Extract with AI, judge for yourself.
pinterestAI bookkeeping, the honest version: use the model to extract receipt fields like date, vendor, and amount into a structured row, but keep the judgment calls human. Why letting AI decide how to categorize spending leaves you with numbers you cannot defend.
bluesky"AI does your bookkeeping." Honest version: the model reads the receipt and pulls fields into a row. It extracts, you decide.
youtubeTitle: AI Bookkeeping, Minus the Hype: Let It Extract, Not Decide
The promise: snap a receipt, AI categorizes everything, taxes done. The honest version: the model reads the receipt and pulls fields into a structured row, which is genuinely useful. But the moment you trust AI judgment on money, you get a ledger you cannot defend to an auditor. Let the model extract, and keep the judgment yours.