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-2kind threadweek W36date 2026-09-08campaign thread · Tuepillar it_devbeat Tueasset videoduration 49.2sground whitescenes 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-W36-Tue-2 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 · 49.2s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–5.0sspatial-parallaxicon·3d-extrude♪ bed_in
Business intelligence used to mean a week-long wait on the data team.
on-screen: Reports waited on the data team
expected on screen: white ground · box hero in the shared Signal Field · Faber leads · node-graph · spatial-parallax · icon·3d-extrude logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape boxground whitetreatment 3d-extrudemotion spatial-parallaxpower summoninstrument summon→Reports waited on the data team
2s2
matches intent
shared field
signature-3d		hook5.0–10.0skinetic-buildicon·wireframe♪ node_lock
By the time the report came back, the question had already changed.
on-screen: By answer time, the question moved
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→By answer time, the question moved
3s3
matches intent
NumberedList
template		teach10.0–15.5skinetic-buildicon·wireframe♪ node_lock
Now we let a model turn a plain English question into the actual query.
on-screen: Now you ask the database in English
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→Now you ask the database in Englishcurate items, nodes
4s4
matches intent
ComparisonTable
template		proof15.5–21.0sreceipts-counticon·wireframe♪ node_lock
It writes the query, runs it, and hands back a clean answer in seconds.
on-screen: It writes the SQL for you
expected on screen: white ground · a ComparisonTable panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ComparisonTablevisual receiptsshape boxground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→It writes the SQL for youcurate colA, colB, rows, statsLabels
5s5
matches intent
CodeWindow
template		diff21.0–26.5scrossfade-8ficon·wireframe♪ node_lock
But a model can write a confident query that quietly asks the wrong thing.
on-screen: A wrong query lies confidently
expected on screen: white ground · a CodeWindow panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id CodeWindowvisual codeshape boxground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→A wrong query lies confidentlycurate codeLines, windowTitle
6s6
matches intent
ChecklistCard
template		teach26.5–32.8skinetic-buildicon·wireframe♪ node_lock
So you always make it show the query, and you read it before you trust it.
on-screen: Always show the query it ran
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→Always show the query it rancurate items, nodes
7s7
matches intent
KpiGrid
template		proof32.8–38.3sreceipts-counticon·wireframe♪ node_lock
Check the logic once, save it, and the whole team reuses a trusted answer.
on-screen: Verify once, then move fast
expected on screen: white ground · a KpiGrid panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id KpiGridvisual receiptsshape boxground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Verify once, then move fastcurate kpis, statsLabels
8s8
matches intent
ListCard
template		step38.3–44.199999999999996skinetic-buildicon·wireframe♪ node_lock
Try it: ask your data a question in English, then read the query it wrote.
on-screen: Ask in English, then read the query
expected on screen: white ground · a ListCard panel over a dimmed Signal Field · Faber leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ListCardvisual pipelineshape boxground whitetreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Ask in English, then read the querycurate items, stages, steps
9s9
matches intent
shared field
signature-3d		resolve44.2–49.2scoalescenceicon·3d-extrude♪ bed_out
Soon anyone can ask the data directly, and the bottleneck quietly disappears.
on-screen: Soon anyone can ask the data
expected on screen: white ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·3d-extrude logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground whitetreatment 3d-extrudemotion coalescencepower coalescenceinstrument coalescence→Soon anyone can ask the data

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)

tiktokStop waiting a week on the data team. Here is the move (AI-assisted): ask your database a question in plain English, let a model write and run the query. Catch: it can be confidently wrong, so always show the query and read it before you trust it. #businessintelligence #data #aitools
instagramStop waiting on the data team. Ask your data in plain English. AI writes the query. Always show the query it ran. Verify once, then move fast. #businessintelligence #dataanalytics #sql #aitools #datadriven
linkedinBusiness intelligence used to mean a week-long wait on the data team, and by then the question had changed. Now a model turns a plain English question into the query, runs it, and returns an answer in seconds. The takeaway: always make it show the query you can read, because a confident model can quietly ask the wrong thing. Verify once, then reuse.
xBI move: ask your database in plain English, let AI write the query. Catch: it can be confidently wrong, so always show the query and read it first. temerarii.com
facebookBusiness intelligence used to mean waiting a week on the data team. Now a model turns a plain English question into the query and returns an answer in seconds. Always show the query and read it first, because a model can be confidently wrong. See the method at temerarii.com.
threadsStop waiting a week on the data team. Ask your database in plain English, let AI write the query. Catch: it can be confidently wrong, so always show the query and read it first.
pinterestAI business intelligence workflow: how to query your data in plain English. Let a model write and run the query, but always show the SQL and verify before you trust it. Evergreen guide to BI, natural language to SQL, and self-serve analytics.
blueskyBI move: ask your database in plain English, let AI write the query. Catch: it can be confidently wrong, so always show the query and read it first. temerarii.com
youtubeAI Business Intelligence: Ask Your Data In Plain English (Safely) BI used to mean a week-long wait on the data team, and by then the question had changed. The real method: let a model turn a plain English question into the actual query, run it, and return an answer in seconds. The catch is real: a model can write a confident query that asks the wrong thing, so always make it show the query and read it before you trust it. Verify once, save it, reuse it. 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