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-W31-Wed-1kind threadweek W31date 2026-08-05campaign thread · Wedpillar it_devbeat Wedasset videoduration 61.8sground redscenes 9

Checklist the per-video bar — engine/sim

86.6/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review social-W31-Wed-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 · 61.8s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–7.0sspatial-parallaxicon·white-knockout♪ bed_in
Business intelligence used to be a monthly report that was already stale by the time you read it.
on-screen: Reports that aged overnight
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · node-graph · spatial-parallax · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape boxground redtreatment white-knockoutmotion spatial-parallaxpower summoninstrument summon→Reports that aged overnight
2s2
matches intent
shared field
signature-3d		hook7.0–13.3skinetic-buildicon·white-knockout♪ node_lock
Dark truth: a metric with no written definition means two people argue past each other forever.
on-screen: A number with no definition lies
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual markshape boxground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→A number with no definition lies
3s3
matches intent
NumberedList
template		teach13.3–19.9skinetic-buildicon·liquid-chrome♪ node_lock
So we do it now by writing each metric's exact definition in one plain line everyone shares.
on-screen: Define each metric in one line
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape boxground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Define each metric in one linecurate items, nodes
4s4
matches intent
ComparisonTable
template		proof19.9–28.0sreceipts-counticon·white-knockout♪ node_lock
Then ask the model to turn a plain question into the query, and you read the query before you trust it.
on-screen: Let the model write the query
expected on screen: red ground · a ComparisonTable panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id ComparisonTablevisual receiptsshape boxground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Let the model write the querycurate colA, colB, rows, statsLabels
5s5
matches intent
BuildLog
template		diff28.0–35.0scrossfade-8ficon·liquid-chrome♪ node_lock
Old way pulled fixed reports. Now you ask a question in words and check the query it wrote.
on-screen: Old: pull reports. Now: ask questions
expected on screen: red ground · a BuildLog panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id BuildLogvisual codeshape boxground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→Old: pull reports. Now: ask questionscurate codeLines, lines
6s6
matches intent
ChecklistCard
template		teach35.0–41.6skinetic-buildicon·white-knockout♪ node_lock
Keep one table as the source of truth, so revenue means the same thing in every chart.
on-screen: One source of truth
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape boxground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→One source of truthcurate items, nodes
7s7
matches intent
KpiGrid
template		proof41.6–48.2sreceipts-counticon·liquid-chrome♪ node_lock
We run this at The Big T-M, and the meeting argues about the decision, not the definition.
on-screen: End the metric argument
expected on screen: red ground · a KpiGrid panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id KpiGridvisual receiptsshape boxground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→End the metric argumentcurate kpis, statsLabels
8s8
matches intent
ListCard
template		step48.2–55.2skinetic-buildicon·white-knockout♪ node_lock
Your move: define each metric once, let the model draft the query, read it, then trust the chart.
on-screen: Steps: define, query, verify
expected on screen: red ground · a ListCard panel over a dimmed Signal Field · Faber leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id ListCardvisual pipelineshape boxground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Steps: define, query, verifycurate items, stages, steps
9s9
matches intent
shared field
signature-3d		resolve55.2–61.800000000000004scoalescenceicon·white-knockout♪ bed_out
Now the numbers agree across the room, and the dashboard stops being a source of new fights.
on-screen: Numbers that agree
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground redtreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→Numbers that agree

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 dashboards spark fights: nobody wrote down what each metric MEANS. Define each one in one plain line, then let AI turn your question into a query, and READ the query before you trust it. (AI-assisted) #businessintelligence #data
instagramDefine each metric in one line. Let AI write the query. Read it before you trust it. One source of truth. #businessintelligence #data #analytics #tech #temerarii
linkedinA metric with no written definition means two people argue past each other forever. Write each metric's exact definition in one plain line, then let a model turn a plain-English question into the query, and read the query before trusting it. Keep one table as the source of truth. Argue about the decision, not the definition.
xYour dashboards spark fights because nobody defined the metrics. Define each in one line. Let AI write the query. Read it before you trust it. temerarii.com
facebookEnd the dashboard arguments: write each metric's definition in one plain line, let AI turn your question into a query, and read the query before you trust the chart. Keep one source of truth. Free method on the site.
threadsA metric with no written definition means two people argue past each other forever. Define each metric in one plain line, let the model write the query, read it before you trust it. Argue about the decision, not the definition.
pinterestBusiness intelligence best practices: write a one-line definition for every metric, use AI to translate plain questions into queries, and keep one source-of-truth table. Trustworthy analytics that ends arguments about what the numbers mean.
blueskyYour dashboards spark fights because nobody defined the metrics. Define each in one line. Let AI write the query. Read it before you trust it. temerarii.com
youtubeBusiness Intelligence That Agrees: Define Metrics, Let AI Query, Verify A metric with no written definition means people argue past each other forever. Write each metric in one plain line, let a model turn a plain question into the query, then read the query before trusting it, and keep one source of truth. Argue about the decision, not the definition. Free 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