Back Office · office.temerarii.xyz
One asset, all the way in — composition, the wireframe + storyboard, the output format stack, and the template, all read from the SAME content-index record. The expected output matches what /media surfaces for this post.
post social-W36-Tue-1kind threadweek W36date 2026-09-08campaign thread · Tuepillar multimediabeat Tueasset videoduration 48.1sground whitescenes 9

Checklist the per-video bar — engine/sim

86.5/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review social-W36-Tue-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

composition SceneReelfamily / template SignalFieldReel
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 · 48.1s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–5.2sspatial-parallaxicon·wireframe♪ bed_in
A great interview used to die inside two hours of raw, unwatched footage.
on-screen: A great interview died in raw footage
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground whitetreatment wireframemotion spatial-parallaxpower summoninstrument summon→A great interview died in raw footage
2s2
matches intent
shared field
signature-3d		hook5.2–10.7skinetic-buildicon·wireframe♪ node_lock
Nobody had time to scrub the tape and dig out the gold buried inside.
on-screen: Nobody had time to dig for gold
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual markshape octaground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→Nobody had time to dig for gold
3s3
matches intent
NumberedList
template		teach10.7–15.7skinetic-buildicon·wireframe♪ node_lock
First move: transcribe the full talk so every word becomes searchable text.
on-screen: Transcribe the whole thing first
expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape octaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Transcribe the whole thing firstcurate items, nodes
4s4
matches intent
RankList
template		proof15.7–20.9sreceipts-counticon·wireframe♪ node_lock
Then ask a model to pull the five most quotable lines with timestamps.
on-screen: Ask AI for the best lines
expected on screen: white ground · a RankList panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id RankListvisual receiptsshape octaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Ask AI for the best linescurate rows, statsLabels
5s5
matches intent
StackTrace
template		diff20.9–25.9scrossfade-8ficon·wireframe♪ node_lock
Auto-generated clips alone feel random and miss the actual story.
on-screen: Auto-clips alone feel random
expected on screen: white ground · a StackTrace panel over a dimmed Signal Field · Lumen leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StackTracevisual codeshape octaground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Auto-clips alone feel randomcurate codeLines, errMsg, errType, fix, frames
6s6
matches intent
ChecklistCard
template		teach25.9–32.199999999999996skinetic-buildicon·wireframe♪ node_lock
So you tell it the one theme you want, and it finds the moments that fit.
on-screen: Tell it the story you want
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape octaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Tell it the story you wantcurate items, nodes
7s7
matches intent
StatScoreboard
template		proof32.2–37.7sreceipts-counticon·wireframe♪ node_lock
A two-hour talk becomes a tight cut that keeps only the parts that land.
on-screen: A two-hour talk becomes a tight cut
expected on screen: white ground · a StatScoreboard panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StatScoreboardvisual receiptsshape octaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→A two-hour talk becomes a tight cutcurate pillar, stats, statsLabels
8s8
matches intent
BlueprintGrid
template		step37.7–42.900000000000006skinetic-buildicon·wireframe♪ node_lock
Try it: transcribe your last interview and ask for quotable lines with times.
on-screen: Transcribe, then ask for timestamps
expected on screen: white ground · a BlueprintGrid panel over a dimmed Signal Field · Lumen leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id BlueprintGridvisual pipelineshape octaground whitetreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Transcribe, then ask for timestampscurate rows, stages, steps
9s9
matches intent
shared field
signature-3d		resolve42.9–48.1scoalescenceicon·wireframe♪ bed_out
Now the gold gets found instead of buried, and the guest gets heard.
on-screen: The gold gets found, not buried
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground whitetreatment wireframemotion coalescencepower coalescenceinstrument coalescence→The gold gets found, not buried

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)

tiktokYour best interview is dying in raw footage. Here is the move (AI-assisted): transcribe the whole talk first, then ask a model for the five most quotable lines with timestamps. Tell it the theme so the clips fit a story, not random cuts. #podcast #interview #aitools
instagramGreat interviews die in raw footage. Transcribe the whole talk. Ask AI for the best lines. Give it the theme. The gold gets found, not buried. #interview #podcasting #contentcreation #aitools #videoediting
linkedinA strong interview used to die inside two hours of raw footage nobody had time to scrub. The method: transcribe the full talk so every word is searchable, then ask a model for the most quotable lines with timestamps, guided by the one theme you want. The takeaway: structure the search and the gold gets found, not buried.
xInterview move: transcribe the whole talk, then ask AI for the five best lines with timestamps. Give it the theme so clips fit a story. The gold gets found. temerarii.com
facebookA great interview used to die inside two hours of raw footage. The method: transcribe the full talk, then ask a model for the most quotable lines with timestamps, guided by your theme. The gold gets found, not buried. See it at temerarii.com.
threadsYour best interview is dying in raw footage. Transcribe the whole talk, ask AI for the five best lines with timestamps, give it the theme. The gold gets found, not buried.
pinterestAI interview editing workflow: how to find the best moments fast. Transcribe the full talk, then ask a model for quotable lines with timestamps guided by your theme. Evergreen guide to podcast editing, interview clips, and video repurposing.
blueskyInterview move: transcribe the whole talk, ask AI for the five best lines with timestamps, give it the theme. The gold gets found, not buried. temerarii.com
youtubeAI Interview Editing: Find The Best Moments In A Two-Hour Talk A great interview used to die inside hours of raw footage nobody had time to scrub. The real method: transcribe the full talk so every word becomes searchable, then ask a model for the five most quotable lines with timestamps. Auto-clips feel random, so tell it the one theme you want and it finds the moments that fit. A long talk becomes a tight cut that keeps only what lands. More at temerarii.com.

Cross-links every lens is a view on this one record

→ Wireframe · scenes→ Calendar week→ Media (audience preview)→ Storyboard hub→ Day view→ Channel view