Checklist the per-video bar — engine/sim
83.3/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W32-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 · 32.3s · 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 | 0–7.2s | kinetic-build | icon·liquid-chrome | ♪ node_lock | AI moderation catches everything automatically, they say. It bans a regular for sarcasm and misses the real troll. on-screen: "AI moderates your community" |
expected on screen: black 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 blacktreatment liquid-chromemotion kinetic-buildpower laser-lockinstrument laser-trace→"AI moderates your community" | |||||||
| 2 |  matches intent CodeWindow template | diff | 7.2–15.899999999999999s | crossfade-8f | icon·ember-fill | ♪ node_lock | What works: the model flags and ranks risk, a human makes the call on anything borderline. AI triages volume, people own judgment. on-screen: Flag, then human reviews |
expected on screen: black ground · a CodeWindow panel over a dimmed Signal Field · Nuntius leads · code · crossfade-8f · icon·ember-fill logo · caption bottom-left spec (the prompt): comp_id CodeWindowvisual codeshape torusground blacktreatment ember-fillmotion crossfade-8fpower morphinstrument morph→Flag, then human reviewscurate codeLines, windowTitle | |||||||
| 3 |  matches intent NumberedList template | teach | 15.9–22.3s | kinetic-build | icon·wireframe | ♪ node_lock | The cost is staffing the review queue, not eliminating it. Set your AI filter to flag, not auto-ban. on-screen: The cost: a human queue |
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Nuntius leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape torusground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→The cost: a human queuecurate items, nodes | |||||||
| 4 |  first render · fix pending KpiGrid templatedead_airgeneric_scene | proof | 22.3–27.3s | receipts-count | icon·white-knockout | ♪ node_lock | Minus the Hype |
expected on screen: black 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 blacktreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate kpis, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 27.3–32.3s | coalescence | icon·wireframe | ♪ bed_out | Minus the Hype |
expected on screen: black ground · torus hero in the shared Signal Field · Nuntius leads · coalescence · coalescence · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape torusground blacktreatment wireframemotion 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 moderates your community," they say. (AI-assisted)
It catches everything automatically? It bans a regular for sarcasm and misses the real troll. What works: the model flags and ranks risk, a human makes the call on anything borderline. AI triages volume, people own judgment. The cost is staffing the review queue, not deleting it.
instagram"AI moderates your community."
It bans a regular for sarcasm and misses the real troll.
What works: the model flags and ranks risk.
A human makes the call on anything borderline.
#temerarii #moderation #communitymanagement #aiethics #trustandsafety
linkedin"AI moderation catches everything automatically." The set-and-forget pitch.
In practice it bans a regular for sarcasm and misses the real troll. Here is what works: the model flags and ranks risk, and a human makes the call on anything borderline. AI triages the volume, people own the judgment.
The cost is staffing the review queue, not eliminating it. Set your AI filter to flag, not auto-ban.
x"AI moderates your community." It bans a regular for sarcasm and misses the real troll.
What works: the model flags and ranks risk, a human decides anything borderline. AI triages volume, people own judgment. The cost is staffing the queue.
facebook"AI moderation catches everything automatically," they say.
It bans a regular for sarcasm and misses the real troll. What works: the model flags and ranks risk, a human makes the call on anything borderline. AI triages volume, people own judgment.
The cost is staffing the review queue, not eliminating it. Set your AI filter to flag, not auto-ban.
threads"AI moderates your community." In practice it bans a regular for sarcasm and misses the real troll.
What works: the model flags and ranks risk, a human makes the call on anything borderline. AI triages volume, people own judgment.
The cost is staffing the review queue. Set your filter to flag, not auto-ban.
pinterestMyth-busting fully automated AI community moderation. Why auto-ban filters punish regulars and miss real trolls, and how flag-then-human-review keeps judgment with people. Trust and safety moderation method.
bluesky"AI moderates your community." It bans a regular for sarcasm and misses the real troll. What works: the model flags and ranks risk, a human decides anything borderline. AI triages volume, people own judgment. Set your filter to flag, not auto-ban.
youtubeThe AI Moderation Myth: Flag and Rank, Then Let a Human Decide
AI moderation catches everything automatically, they say. It bans a regular for sarcasm and misses the real troll. What works: the model flags and ranks risk, a human makes the call on anything borderline. AI triages volume, people own judgment. The cost is staffing the review queue, not eliminating it. Set your AI filter to flag, not auto-ban. AI-assisted production by Temerarii.