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-W25-Mon-1kind threadweek W25date 2026-06-22campaign thread · Monpillar multimediabeat Monasset videoduration 49.7sground whitescenes 9

Checklist the per-video bar — engine/sim

98.5/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review social-W25-Mon-1 good|bad)
⚠ 1 flag(s) — not yet ship-ready: copy_generic · 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 · 49.7s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–6.3sspatial-parallaxicon·3d-extrude♪ bed_in
The old way of taping an interview meant a crew, a room, and a long day.
on-screen: Interviews used to take a full crew
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·3d-extrude logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground whitetreatment 3d-extrudemotion spatial-parallaxpower summoninstrument summon→Interviews used to take a full crew
2s2
matches intent
shared field
signature-3d		hook6.3–12.2skinetic-buildicon·wireframe♪ node_lock
Most of that day was prep, scribbled notes, and hoping you asked the right thing.
on-screen: Most of the day was prep
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→Most of the day was prep
3s3
matches intent
NumberedList
template		teach12.2–17.4skinetic-buildicon·wireframe♪ node_lock
The fix that still holds: build a question tree before anyone sits down.
on-screen: Build the question tree 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→Build the question tree firstcurate items, nodes
4s4
matches intent
ComparisonTable
template		proof17.4–22.599999999999998sreceipts-counticon·wireframe♪ node_lock
Each likely answer points to the next sharper question, so you never stall.
on-screen: Each answer points to next question
expected on screen: white ground · a ComparisonTable panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ComparisonTablevisual receiptsshape octaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Each answer points to next questioncurate colA, colB, rows, statsLabels
5s5
matches intent
BuildLog
template		diff22.6–28.1scrossfade-8ficon·wireframe♪ node_lock
A clever room without a plan rambles. A plan makes a small setup shine.
on-screen: A plan beats a clever room
expected on screen: white ground · a BuildLog panel over a dimmed Signal Field · Lumen leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id BuildLogvisual codeshape octaground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→A plan beats a clever roomcurate codeLines, lines
6s6
matches intent
ChecklistCard
template		teach28.1–34.0skinetic-buildicon·wireframe♪ node_lock
Now we feed the topic to a model and it drafts the follow-up branches fast.
on-screen: Now AI drafts the follow-ups
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→Now AI drafts the follow-upscurate items, nodes
7s7
matches intent
KpiGrid
template		proof34.0–39.0sreceipts-counticon·wireframe♪ node_lock
Those branches sit on your lap, ready, before the conversation starts.
on-screen: Branches ready before the chat
expected on screen: white ground · a KpiGrid panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id KpiGridvisual receiptsshape octaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Branches ready before the chatcurate kpis, statsLabels
8s8
matches intent
CheatSheet
template		step39.0–44.2skinetic-buildicon·wireframe♪ node_lock
Map the likely answers, branch your questions, then tape with a small kit.
on-screen: Map answers, branch questions, then tape
expected on screen: white ground · a CheatSheet panel over a dimmed Signal Field · Lumen leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id CheatSheetvisual pipelineshape octaground whitetreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Map answers, branch questions, then tapecurate points, stages, steps, uses
9s9
matches intent
shared field
signature-3d		resolve44.2–49.7scoalescenceicon·3d-extrude♪ bed_out
The Big T-M spends the prep on the question tree, not on hauling gear.
on-screen: The Big T-M plans the talk
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·3d-extrude logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground whitetreatment 3d-extrudemotion coalescencepower coalescenceinstrument coalescence→The Big T-M plans the talk

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)

tiktokWhy your interview rambles (AI-assisted fix): you didn't build a question tree. Map the likely answers, branch the next question off each, and you never stall. Let AI draft the follow-up branches. #interviews #podcasting #contentcreation
instagramInterviews ramble when there's no plan. Build a question tree first. Each answer points to the next question. #interviews #podcast #contentcreation #filmmaking #storytelling
linkedinA good interview is not about gear, it is about a question tree. Map the likely answers, then branch the next, sharper question off each. The takeaway: spend prep on structure, not equipment. We let a model draft the follow-up branches so the conversation never stalls.
xInterviews ramble because there's no question tree. Map likely answers, branch the next question off each. AI can draft the branches. temerarii.xyz
facebookTaping an interview used to eat a whole day. The thing that actually fixes a rambling chat is a question tree: map the likely answers and branch the next question off each. AI drafts the branches now. Read the method on the site.
threadsThe reason interviews ramble: no question tree. Map what they'll likely say, branch the next question off each answer, and you never stall. AI can draft those branches for you.
pinterestInterview prep method: build a question tree before you record. Map the likely answers and branch the next question off each so the conversation never stalls. Interview tips, podcasting workflow, content creation.
blueskyInterviews ramble without a question tree. Map likely answers, branch the next question off each. AI can draft the branches. temerarii.xyz
youtubeThe Question Tree: Why Your Interviews Ramble A full crew and a clever room won't save an unplanned interview. We show the method that still holds: build a question tree first, mapping likely answers and branching the next sharper question off each, so you never stall. Then let a model draft the follow-up branches before you record.

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

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