Checklist the per-video bar — engine/sim
86.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W36-Mon-3 good|bad)⚠ 3 flag(s) — not yet ship-ready: copy_genericdup_sequence_across_assetsdup_set_across_assets · see docs/strategy/VIDEO-CHECKLIST.md
Composition comp · template family · expected output
9:16 Reelpending1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
render pending — silent master not yet on disk
expected output: 0/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 9 scenes · 48.8s · 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 | open | 0–5.2s | spatial-parallax | icon·white-knockout | ♪ bed_in | Advertising used to mean betting a budget on one big idea and praying. on-screen: Ads used to mean one big bet |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · node-graph · spatial-parallax · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape coneground redtreatment white-knockoutmotion spatial-parallaxpower summoninstrument summon→Ads used to mean one big bet | |||||||
| 2 |  matches intent shared field signature-3d | hook | 5.2–10.4s | kinetic-build | icon·white-knockout | ♪ node_lock | You waited weeks just to learn the winning ad was actually a flop. on-screen: You waited weeks to learn it flopped |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape coneground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→You waited weeks to learn it flopped | |||||||
| 3 |  matches intent NumberedList template | teach | 10.4–16.7s | kinetic-build | icon·liquid-chrome | ♪ node_lock | Now we ask a model for ten angles on the same offer in a single pass. on-screen: Now we generate ten angles fast |
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→Now we generate ten angles fastcurate items, nodes | |||||||
| 4 |  matches intent ComparisonTable template | proof | 16.7–22.2s | receipts-count | icon·white-knockout | ♪ node_lock | We spend a tiny amount testing all ten before we scale a single one. on-screen: Test small before you scale |
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→Test small before you scalecurate colA, colB, rows, statsLabels | |||||||
| 5 |  matches intent JsonDiff template | diff | 22.2–27.2s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | Pumping out more ads alone is just louder noise, not better results. on-screen: More ads alone is just noise |
expected on screen: red ground · a JsonDiff panel over a dimmed Signal Field · Augur leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape coneground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→More ads alone is just noisecurate codeLines, fileName, lines | |||||||
| 6 |  matches intent ChecklistCard template | teach | 27.2–32.4s | kinetic-build | icon·white-knockout | ♪ node_lock | So you let the click data, not the meeting, pick which angle survives. on-screen: Let the click data pick winners |
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape coneground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Let the click data pick winnerscurate items, nodes | |||||||
| 7 |  matches intent KpiGrid template | proof | 32.4–37.9s | receipts-count | icon·liquid-chrome | ♪ node_lock | Money flows to the angle that earns it, and the rest gets cut fast. on-screen: Money flows to what actually works |
expected on screen: red ground · a KpiGrid panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id KpiGridvisual receiptsshape coneground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Money flows to what actually workscurate kpis, statsLabels | |||||||
| 8 |  matches intent PipelineMap template | step | 37.9–43.8s | kinetic-build | icon·white-knockout | ♪ node_lock | Try it: draft ten angles, test them cheap, and fund only the one that wins. on-screen: Draft ten angles, fund the winner |
expected on screen: red ground · a PipelineMap panel over a dimmed Signal Field · Augur leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id PipelineMapvisual pipelineshape coneground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Draft ten angles, fund the winnercurate stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 43.8–48.8s | coalescence | icon·white-knockout | ♪ bed_out | Soon the budget steers itself toward whatever the audience keeps clicking. on-screen: Soon the budget steers itself |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground redtreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→Soon the budget steers itself | |||||||
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)
tiktokStop betting the budget on one big ad. Here is the move (AI-assisted): ask a model for ten angles on the same offer, test all of them cheap, then let the click data pick the winner. Money flows to what works, the rest gets cut. #advertising #marketingtips #aitools
instagramOne big ad bet is over.
Generate ten angles fast.
Test them all cheap.
Let the clicks pick the winner.
Fund only what works.
#advertising #digitalmarketing #adtesting #aitools #growth
linkedinAdvertising used to mean betting a budget on one big idea and waiting weeks to learn it flopped. Now we generate ten angles on the same offer, test them cheaply, and let click data pick the survivor. The takeaway: money should follow evidence, not the loudest opinion in the meeting. Receipts over hype.
xAdvertising move: generate ten angles on one offer, test them cheap, let the click data fund the winner. Stop betting the budget on one big idea. temerarii.com
facebookAdvertising used to mean betting the budget on one big idea and praying. Now we generate ten angles, test them cheaply, and let click data pick the winner. Money flows to what works. See the method at temerarii.com.
threadsStop betting the budget on one big ad. Generate ten angles, test them cheap, let the click data pick the winner. Money flows to what works, the rest gets cut.
pinterestAI advertising workflow: how to find a winning ad without betting the budget. Generate ten angles on one offer, test them cheaply, and let click data fund the winner. Evergreen guide to ad testing, paid media strategy, and creative iteration.
blueskyAdvertising move: generate ten angles on one offer, test them cheap, let the clicks fund the winner. Stop betting the budget on one big idea. temerarii.com
youtubeAI Advertising: Test Ten Angles, Fund Only The Winner
Advertising used to mean betting a budget on one big idea and waiting weeks to learn it flopped. The real method: ask a model for ten angles on the same offer, spend a tiny amount testing all of them, then let the click data, not the meeting, pick which angle survives. Money flows to the angle that earns it and the rest gets cut fast. Draft ten angles and fund the winner. More at temerarii.com.