Checklist the per-video bar — engine/sim
86.5/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W34-Sun-1 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 | 0–5.0s | spatial-parallax | icon·white-knockout | ♪ bed_in | Most shops hide the method and sell the mystery. on-screen: We give the method away |
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · node-graph · spatial-parallax · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape boxground redtreatment white-knockoutmotion spatial-parallaxpower summoninstrument summon→We give the method away | |||||||
| 2 |  matches intent shared field signature-3d | hook | 5.0–10.0s | kinetic-build | icon·white-knockout | ♪ node_lock | A method nobody understands dies the day you leave the room. on-screen: Hidden methods do not scale |
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape boxground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→Hidden methods do not scale | |||||||
| 3 |  matches intent NumberedList template | teach | 10.0–15.2s | kinetic-build | icon·liquid-chrome | ♪ node_lock | We teach by writing the recipe down: the prompt, the model, the check. on-screen: Write the recipe down |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape boxground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Write the recipe downcurate items, nodes | |||||||
| 4 |  matches intent ComparisonTable template | proof | 15.2–20.7s | receipts-count | icon·white-knockout | ♪ node_lock | Last month a brand-new hire ran our whole pipeline alone by reading the doc. on-screen: A new hire ran it solo |
expected on screen: red ground · a ComparisonTable panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ComparisonTablevisual receiptsshape boxground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→A new hire ran it solocurate colA, colB, rows, statsLabels | |||||||
| 5 |  matches intent BuildLog template | diff | 20.7–25.7s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | Gatekeepers keep one person smart; open teaching makes the room smart. on-screen: Open teaching beats gatekeeping |
expected on screen: red ground · a BuildLog panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id BuildLogvisual codeshape boxground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→Open teaching beats gatekeepingcurate codeLines, lines | |||||||
| 6 |  matches intent ChecklistCard template | teach | 25.7–31.6s | kinetic-build | icon·white-knockout | ♪ node_lock | Now we record a short loom, paste the exact prompt, and version it like code. on-screen: Record the loom, save the prompt |
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape boxground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Record the loom, save the promptcurate items, nodes | |||||||
| 7 |  matches intent KpiGrid template | proof | 31.6–36.6s | receipts-count | icon·liquid-chrome | ♪ node_lock | Our onboarding went from a quiet week to a single shared afternoon. on-screen: Onboarding dropped to one day |
expected on screen: red ground · a KpiGrid panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id KpiGridvisual receiptsshape boxground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Onboarding dropped to one daycurate kpis, statsLabels | |||||||
| 8 |  matches intent StepFlow template | step | 36.6–42.9s | kinetic-build | icon·white-knockout | ♪ node_lock | Your step: pick one task, write the prompt, name one owner, store it in one doc. on-screen: One prompt, one owner, one doc |
expected on screen: red ground · a StepFlow panel over a dimmed Signal Field · Faber leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id StepFlowvisual pipelineshape boxground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→One prompt, one owner, one doccurate stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 42.9–48.8s | coalescence | icon·white-knockout | ♪ bed_out | If you can teach it, the AI can scale it. That is the whole game. on-screen: Teach it, then it scales |
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground redtreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→Teach it, then it scales | |||||||
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)
tiktokPOV: your best worker leaves and takes the method with them. We fix that by writing the recipe down. The Big T-M teaches the exact prompt, model, and check, then a new hire runs it solo. Open beats gatekeeping. (AI-assisted) Steal the doc template in bio.
instagramHidden methods die when people leave.
We write the recipe down: prompt, model, check.
Then anyone can run it.
That is staff training that scales.
#stafftraining #aiworkflow #smallbusiness #marketingops #temerarii
linkedinMost agencies sell the mystery and hide the method. We do the opposite. Every AI task here ships with a written recipe: the exact prompt, the model used, and the check that proves it worked. The result is plain: a new hire ran our full pipeline alone by reading the doc. Takeaway: if you can teach a method, AI can scale it. If you can't, it dies the day your best person leaves.
xHidden methods die when people leave. Write the recipe down: prompt, model, check. Then anyone can run it. That's training that scales. temerarii.xyz
facebookMost shops hide the method and sell the mystery. We write the recipe down instead, the exact prompt, the model, and the check. A brand-new hire ran our whole pipeline alone just by reading the doc. If you can teach it, AI can scale it. Want the doc template? Comment and we'll send it.
threadsYour best worker leaves and the method walks out the door with them.
Fix: write the recipe down. Prompt, model, check. One owner, one doc.
Now a new hire runs it solo. Teach it, then it scales.
pinterestHow to train staff on AI workflows that actually scale: write the recipe down, the exact prompt, the model you used, and the check that proves it worked. One task, one owner, one shared doc. Open teaching beats gatekeeping every time. Staff training, AI onboarding, marketing operations, small business systems.
blueskyHidden methods die when people leave. Write the recipe down: prompt, model, check. Then anyone runs it. Teach it and it scales. temerarii.xyz
youtubeOpen by Design: Give the Method Away So AI Can Scale It
Most shops hide their method and sell the mystery, then it dies the day their best person leaves. We do the opposite. Every AI task ships with a written recipe: the exact prompt, the model, and the check that proves it worked. We record a short loom, paste the prompt, and version it like code. A brand-new hire ran our full pipeline alone just by reading the doc, and onboarding dropped from a quiet week to one shared afternoon.
Your step: pick one task, write the prompt, name one owner, store it in one doc. If you can teach it, AI can scale it.
AI-assisted production. More at temerarii.xyz