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-2kind threadweek W25date 2026-06-22campaign thread · Monpillar it_devbeat Monasset videoduration 48.5sground 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-2 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 · 48.5s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–5.9sspatial-parallaxicon·color♪ bed_in
The old way built a dashboard and left you to stare at it for answers.
on-screen: Dashboards used to just sit there
expected on screen: white ground · box hero in the shared Signal Field · Faber leads · node-graph · spatial-parallax · icon·color logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape boxground whitetreatment colormotion spatial-parallaxpower summoninstrument summon→Dashboards used to just sit there
2s2
matches intent
shared field
signature-3d		hook5.9–11.4skinetic-buildicon·wireframe♪ node_lock
Here is where this goes: you ask your data a question in plain words.
on-screen: Soon you ask it plainly
expected on screen: white ground · box hero in the shared Signal Field · Faber leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual markshape boxground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→Soon you ask it plainly
3s3
matches intent
NumberedList
template		teach11.4–16.6skinetic-buildicon·wireframe♪ node_lock
Point a model at your tables and tell it what the columns mean.
on-screen: Point the model at your tables
expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape boxground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Point the model at your tablescurate items, nodes
4s4
matches intent
RankList
template		proof16.6–22.5sreceipts-counticon·wireframe♪ node_lock
Ask why sales dipped last week and it writes the query and draws the chart.
on-screen: Ask in words, get the chart back
expected on screen: white ground · a RankList panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id RankListvisual receiptsshape boxground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Ask in words, get the chart backcurate rows, statsLabels
5s5
matches intent
DiffCard
template		diff22.5–28.0scrossfade-8ficon·wireframe♪ node_lock
A dashboard makes you hunt. A model that knows your tables lets you ask.
on-screen: Stop hunting; start asking
expected on screen: white ground · a DiffCard panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id DiffCardvisual codeshape boxground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Stop hunting; start askingcurate codeLines, lines
6s6
matches intent
ChecklistCard
template		teach28.0–33.0skinetic-buildicon·wireframe♪ node_lock
Save the good questions so they refresh as living views, not one-offs.
on-screen: Save the answers as living views
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape boxground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Save the answers as living viewscurate items, nodes
7s7
matches intent
StatScoreboard
template		proof33.0–38.0sreceipts-counticon·wireframe♪ node_lock
Ask once, and the same answer updates itself every week without you.
on-screen: Ask once, it answers every week
expected on screen: white ground · a StatScoreboard panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StatScoreboardvisual receiptsshape boxground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Ask once, it answers every weekcurate pillar, stats, statsLabels
8s8
matches intent
StepFlow
template		step38.0–43.0skinetic-buildicon·wireframe♪ node_lock
Define your columns, ask in plain words, then save the useful answers.
on-screen: Define columns, ask, then save the view
expected on screen: white ground · a StepFlow panel over a dimmed Signal Field · Faber leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StepFlowvisual pipelineshape boxground whitetreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Define columns, ask, then save the viewcurate stages, steps
9s9
matches intent
shared field
signature-3d		resolve43.0–48.5scoalescenceicon·color♪ bed_out
The Big T-M is building data that answers back instead of just sitting there.
on-screen: The Big T-M makes data answer back
expected on screen: white ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·color logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground whitetreatment colormotion coalescencepower coalescenceinstrument coalescence→The Big T-M makes data answer back

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)

tiktokWhere business dashboards are heading (AI-assisted): you stop hunting charts and just ask your data in plain words. Point a model at your tables, tell it the columns, ask why sales dipped. It writes the query. #businessintelligence #dataanalytics #BI
instagramDashboards make you hunt. Soon you just ask your data. "Why did sales dip last week?" #businessintelligence #dataanalytics #BI #data #analytics
linkedinDashboards make people hunt for answers. The coming shift: you ask your data a question in plain language and a model that understands your tables writes the query and returns the chart. The takeaway: define your columns well, then save the good questions as living views that refresh on their own.
xDashboards make you hunt. Soon you ask your data in plain words and a model writes the query. Define your columns, then save the views. temerarii.xyz
facebookA dashboard just sits there and makes you hunt for the answer. The shift coming: you ask your data in plain words, and a model that knows your tables writes the query and draws the chart. See how it works on the site.
threadsSoon you won't read dashboards, you'll talk to them. Point a model at your tables, define the columns, then ask "why did sales dip?" It writes the query and draws the chart.
pinterestConversational business intelligence explained: instead of hunting through dashboards, ask your data in plain words and let a model write the query. Define your columns and save living views. Data analytics tips, BI strategy, business intelligence.
blueskyDashboards make you hunt. Soon you just ask your data in plain words and a model writes the query. temerarii.xyz
youtubeFrom Dashboards to Conversations: The Future of BI A dashboard makes you hunt for answers. We walk through the shift: point a model at your tables, tell it what the columns mean, then ask questions in plain language. It writes the query and returns the chart. Save the good questions as living views that refresh on their own.

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

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