Checklist the per-video bar — engine/sim
98.5/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W27-Mon-3 good|bad)⚠ 1 flag(s) — not yet ship-ready: copy_generic · 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 · 63.2s · 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 | 0–7.3s | spatial-parallax | icon·liquid-chrome | ♪ bed_in | You used to film an event, then wait three weeks for an editor to hand back one tired recap. on-screen: Event recaps used to take weeks |
expected on screen: red ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground redtreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→Event recaps used to take weeks | |||||||
| 2 |  matches intent shared field signature-3d | hook | 7.3–14.3s | kinetic-build | icon·white-knockout | ♪ node_lock | By the time it shipped, the room had gone home and the buzz had already cooled to nothing. on-screen: By then nobody cared |
expected on screen: red ground · octa hero in the shared Signal Field · Lumen leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape octaground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→By then nobody cared | |||||||
| 3 |  matches intent NumberedList template | teach | 14.3–22.0s | kinetic-build | icon·liquid-chrome | ♪ node_lock | Now you record the audio live and let a model transcribe it, so clips get cut while the event runs. on-screen: Cut clips while the event runs |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape octaground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Cut clips while the event runscurate items, nodes | |||||||
| 4 |  matches intent RankList template | proof | 22.0–28.3s | receipts-count | icon·white-knockout | ♪ node_lock | With a timestamped transcript, you find the best forty seconds by searching words, not scrubbing tape. on-screen: Search the talk by keyword |
expected on screen: red ground · a RankList panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape octaground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Search the talk by keywordcurate rows, statsLabels | |||||||
| 5 |  matches intent CodeWindow template | diff | 28.3–34.9s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | One keynote stops being one video. It becomes thirty short clips, each aimed at a different room. on-screen: One event, thirty posts |
expected on screen: red ground · a CodeWindow panel over a dimmed Signal Field · Lumen leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id CodeWindowvisual codeshape octaground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→One event, thirty postscurate codeLines, windowTitle | |||||||
| 6 |  matches intent ChecklistCard template | teach | 34.9–41.9s | kinetic-build | icon·white-knockout | ♪ node_lock | Feed each clip's transcript back to a model and it drafts the caption for every platform in seconds. on-screen: Let it draft every caption |
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape octaground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Let it draft every captioncurate items, nodes | |||||||
| 7 |  matches intent StatScoreboard template | proof | 41.9–48.9s | receipts-count | icon·liquid-chrome | ♪ node_lock | The best moment hits the feed while attendees are still in the lobby, phones already out and scrolling. on-screen: Posted before the lobby clears |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape octaground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Posted before the lobby clearscurate pillar, stats, statsLabels | |||||||
| 8 |  matches intent StepFlow template | step | 48.9–55.9s | kinetic-build | icon·white-knockout | ♪ node_lock | So the move is transcribe live, search for gold, clip it, and let the model draft each caption. on-screen: Step: transcribe, search, clip, caption |
expected on screen: red ground · a StepFlow panel over a dimmed Signal Field · Lumen leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id StepFlowvisual pipelineshape octaground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Step: transcribe, search, clip, captioncurate stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 55.9–63.199999999999996s | coalescence | icon·liquid-chrome | ♪ bed_out | Cover the event at the speed it happens. The Big T-M turns one room into a week of posts. on-screen: Cover it at the speed it happens |
expected on screen: red ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Cover it at the speed it happens | |||||||
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)
tiktokEvent coverage at the speed it happens (AI-assisted). Skip the 3-week edit. Record audio live, let a model transcribe it, then find your best 40 seconds by SEARCHING the words instead of scrubbing tape. One keynote becomes 30 clips, each aimed at a different room. Posted while attendees are still in the lobby.
instagramStop waiting 3 weeks for a recap.
Transcribe the event live.
Search the talk for gold.
One keynote = 30 clips.
Posted before the lobby clears.
#eventcoverage #eventmarketing #videocontent #contentstrategy #livestream
linkedinEvent coverage used to mean filming a keynote, then waiting three weeks for one tired recap, by which point the buzz had cooled.
The faster workflow:
1. Record the audio live and have a model transcribe it in near real time.
2. Use the timestamped transcript to find your best forty seconds by searching words, not scrubbing tape.
3. Treat one keynote as thirty short clips, each aimed at a different audience, and let the model draft the caption for each platform.
The payoff: the strongest moment hits feeds while attendees are still in the lobby. You cover the event at the speed it actually happens, and one room becomes a week of content. AI-assisted and disclosed.
xStop waiting 3 weeks for an event recap. Transcribe the audio live, search the transcript for your best 40 seconds, and turn one keynote into 30 clips. Posted before the lobby clears. temerarii.com
facebookEvent coverage used to mean a three-week wait for one tired recap. Now: record audio live, let a model transcribe it, and find your best forty seconds by searching the words instead of scrubbing tape. One keynote becomes thirty clips, each aimed at a different audience, with AI-drafted captions. The best moment posts while attendees are still in the lobby. See how at temerarii.com.
threadsStop waiting 3 weeks for an event recap. Transcribe the audio live, search the transcript for your best 40 seconds, and turn one keynote into 30 clips. Posted before the lobby clears.
pinterestFaster event coverage workflow: transcribe the audio live, search the transcript for the best moments, clip them, and auto-draft captions. An evergreen method to turn one keynote into 30 social clips while the event is still happening.
blueskyStop waiting 3 weeks for an event recap. Transcribe the audio live, search the transcript for your best 40 seconds, turn one keynote into 30 clips. Posted before the lobby clears. temerarii.com
youtubeReal-Time Event Coverage: Live Transcription, Searchable Clips & Auto Captions
Event coverage used to mean a three-week wait for one tired recap, by which point the buzz had cooled. This shows a faster path: record audio live and let a model transcribe it, use the timestamped transcript to find your best forty seconds by searching words instead of scrubbing tape, and turn one keynote into thirty clips aimed at different audiences with AI-drafted captions. The strongest moment hits feeds while attendees are still in the lobby. AI-assisted and disclosed. More at temerarii.com.