Checklist the per-video bar — engine/sim
95.3/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W24-Thu good|bad)⚠ 2 flag(s) — not yet ship-ready: copy_genericdead_air · 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 · 33.5s · 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 | 0–7.0s | kinetic-build | icon·liquid-chrome | ♪ node_lock | The outbound crowd promise AI writes a thousand cold emails and they all convert. Your spam folder disagrees. on-screen: "AI writes your cold emails" |
expected on screen: red ground · torus hero in the shared Signal Field · Nuntius leads · mark · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape torusground redtreatment liquid-chromemotion kinetic-buildpower laser-lockinstrument laser-trace→"AI writes your cold emails" | |||||||
| 2 |  matches intent JsonDiff template | diff | 7.0–15.6s | crossfade-8f | icon·white-knockout | ♪ node_lock | What works: scrape a real trigger, a funding round, a new hire, a job post, then let AI write one line about that. on-screen: Trigger, then personalize |
expected on screen: red ground · a JsonDiff panel over a dimmed Signal Field · Nuntius leads · code · crossfade-8f · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape torusground redtreatment white-knockoutmotion crossfade-8fpower morphinstrument morph→Trigger, then personalizecurate codeLines, fileName, lines | |||||||
| 3 |  first render · fix pending NumberedList templatedead_air | teach | 15.6–20.6s | kinetic-build | icon·liquid-chrome | ♪ node_lock | The real cost is research per lead, not volume. on-screen: The cost: a real reason |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Nuntius leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape torusground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→The cost: a real reasoncurate items, nodes | |||||||
| 4 |  matches intent KpiGrid template | proof | 20.6–26.5s | receipts-count | icon·white-knockout | ♪ node_lock | Test it yourself. Ten researched leads against a hundred blasted ones. Count replies, not sends. on-screen: Count replies, not sends |
expected on screen: red ground · a KpiGrid panel over a dimmed Signal Field · Nuntius leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id KpiGridvisual receiptsshape torusground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Count replies, not sendscurate kpis, statsLabels | |||||||
| 5 |  matches intent shared field signature-3d | resolve | 26.5–33.5s | coalescence | icon·liquid-chrome | ♪ bed_out | The robot writes fine. It just cannot care. That part is still yours. The Big T-M, signing off. on-screen: Care is the moat |
expected on screen: red ground · torus hero in the shared Signal Field · Nuntius leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape torusground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Care is the moat | |||||||
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)
tiktokThe pitch: AI writes a thousand cold emails and they all convert. Your spam folder disagrees. What works: scrape a real trigger, a funding round, a new hire, then let AI write one line about that. The cost is research per lead, not volume. (AI-assisted)
instagram"AI writes a thousand cold emails that all convert."
Your spam folder disagrees.
What actually works:
Scrape a real trigger. A funding round. A new hire. A job post.
Let AI write one line about that.
The cost is research per lead, not volume.
#coldemail #outbound #sales #ai #b2b
linkedinThe outbound crowd promises that AI writes a thousand cold emails and they all convert. Your spam folder disagrees.
Here is what works. You scrape a real trigger first: a funding round, a new hire, a job post. Then you let AI write one line about that specific thing. The model is good at phrasing, not at finding a reason to reach out.
The real cost is research per lead, not volume. That is why the thousand-email approach fails and the slower one lands.
xThe pitch: AI writes 1,000 cold emails that all convert. Your spam folder disagrees. What works: scrape a real trigger, then let AI write one line about it. The cost is research per lead, not volume. temerarii.com
facebookThe outbound crowd promises AI will write a thousand cold emails that all convert. Your spam folder disagrees. What actually works is smaller: scrape a real trigger like a funding round or a new hire, then let AI write one line about that. The real cost is research per lead, not volume. Try it on your next ten prospects.
threadsThe pitch: AI writes a thousand cold emails and they all convert. Your spam folder disagrees.
What works: scrape a real trigger, a funding round, a new hire, a job post, then let AI write one line about that. The cost is research per lead, not volume. Slower, but it lands.
pinterestCold email with AI, minus the hype: why volume fails. The thousand-email blast lands in spam. The move that works is scraping a real trigger per lead, a funding round or a new hire, then letting AI write one line about it. The real cost is research per lead, not volume. A practical outbound guide.
blueskyThe pitch: AI writes 1,000 cold emails that all convert. Your spam folder disagrees. What works: scrape a real trigger, let AI write one line about it. The cost is research per lead, not volume.
youtubeTitle: AI Cold Emails That Convert? The Part the Pitch Skips
The outbound crowd promises AI writes a thousand cold emails and they all convert. Your spam folder disagrees. What actually works: scrape a real trigger, a funding round, a new hire, a job post, then let AI write one line about that. The real cost is research per lead, not volume. We show the honest version of AI outbound.