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 longform-W49-Frikind longformweek W49date 2026-12-11campaign longform-youtubepillar emerging_techbeat asset videoduration 143.2sground blackscenes 8

Checklist the per-video bar — engine/sim

96.7/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review longform-W49-Fri good|bad)
⚠ 2 flag(s) — not yet ship-ready: custom_element_dup · see docs/strategy/VIDEO-CHECKLIST.md

Composition comp · template family · expected output

composition LongFormChaptersfamily / template LongFormChapters
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 8 scenes · 143.2s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–22.0sspatial-parallaxicon·liquid-chrome♪ bed_in
The week says see it, and today we deliver that. We open business intelligence, the plain art of turning the numbers you already have into a picture you can act on. By the end you will know how to pull your own data and let a model read it back to you, instead of staring at a wall of cells.
on-screen: See it, finally
expected on screen: black ground · cone hero in the shared Signal Field · Augur leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape coneground blacktreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→See it, finally
2s2
first render · fix pending
ChecklistCard
templatecustom_element_dup
teach22.0–40.0skinetic-buildicon·wireframe♪ node_lock
The first move is to get the real numbers in one place. Wire an MCP server into the tool that holds them, your analytics, your sales sheet, your search console, and pull the rows down. Not a screenshot, the actual data. You cannot understand a number you cannot reach.
on-screen: Pull your own data first
expected on screen: black ground · a ChecklistCard panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Pull your own data firstcurate items, nodes
3s3
matches intent
NumberedList
template
teach40.0–58.8skinetic-buildicon·wireframe♪ node_lock
The second move is to ask the model a plain question of that data. What went up last week, and what went down. Make it answer in one sentence a child would follow. The skill is not big words. It is forcing the answer to be small enough to act on.
on-screen: Ask the dumb question on purpose
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Ask the dumb question on purposecurate items, nodes
4s4
matches intent
SchematicCard
template
teach58.8–76.8skinetic-buildicon·wireframe♪ node_lock
The third move is one picture, not a dashboard with forty boxes. Tell the agent to draw the single chart that answers your question, then look at it. A good chart makes the decision obvious in two seconds. If you have to study it, it is the wrong chart.
on-screen: Make one chart that matters
expected on screen: black ground · a SchematicCard panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id SchematicCardvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Make one chart that matterscurate nodes
5s5
matches intent
ProcessFlow
template
teach76.8–94.1skinetic-buildicon·wireframe♪ node_lock
The fourth move is the one people forget. Every number must end in a do. The page that loses people, the email that nobody opens, the product nobody finds. The point of seeing it is to change something this week, not to feel informed and do nothing.
on-screen: Turn the number into a move
expected on screen: black ground · a ProcessFlow panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ProcessFlowvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Turn the number into a movecurate nodes, steps
6s6
first render · fix pending
CheatSheet
templatecustom_element_dup
teach94.1–112.1skinetic-buildicon·wireframe♪ node_lock
The proof is this studio runs on its own data the same way, pulled with the same tools, read back in plain words, turned into the next move. We do not hide the dashboard. The whole thing was built so you could watch the decisions, not just the output.
on-screen: We read our own numbers in public
expected on screen: black ground · a CheatSheet panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id CheatSheetvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→We read our own numbers in publiccurate nodes, points, uses
7s7
matches intent
KpiGrid
template
proof112.1–127.3sreceipts-counticon·wireframe♪ node_lock
So business intelligence is small on purpose: pull the real data, ask a plain question, draw one chart, pick one move. The tools are free. The discipline is the part. Tomorrow we make sure everyone can actually use what we build.
on-screen: One picture, one decision
expected on screen: black ground · a KpiGrid panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id KpiGridvisual receiptsshape coneground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→One picture, one decisioncurate kpis, statsLabels
8s8
matches intent
shared field
signature-3d
resolve127.3–143.2scoalescenceicon·liquid-chrome♪ bed_out
Seeing it is the whole reward for running it and securing it. If you cannot read your own machine, you do not own it. Go look at how we read ours at office.temerarii.xyz, and try the same pull on your own numbers tonight.
on-screen: See the numbers at office.temerarii.xyz
expected on screen: black ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground blacktreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→See the numbers at office.temerarii.xyz

Format stack 1 aspects · same scenes[], re-cropped

16:9
1920×1080
X/Twitter · YouTube · LinkedIn video

Channels 2 destinations

YouTubeBlog

Social captions supplemental published copy · per channel (comp_id level)

youtubeBusiness intelligence the small way: pull your data, ask one plain question Business intelligence is the plain art of turning numbers you already have into a picture you can act on. By the end of this video you will know how to pull your own data and let a model read it back to you, instead of staring at a wall of cells. The four moves: - Pull your own data first. Wire an MCP server into the tool that holds your numbers, like your analytics, your sales sheet, or search console, and pull the rows down. Not a screenshot, the actual data. You cannot understand a number you cannot reach. - Ask the dumb question on purpose. Ask the model a plain question of that data: what went up last week, and what went down. Make it answer in one sentence a child would follow. The skill is forcing the answer to be small enough to act on. - Make one chart that matters. Tell the agent to draw the single chart that answers your question, not a dashboard with forty boxes. A good chart makes the decision obvious in two seconds. If you have to study it, it is the wrong chart. - Turn the number into a move. Every number must end in a do. The page that loses people, the email nobody opens, the product nobody finds. The point of seeing it is to change something this week, not to feel informed and do nothing. The proof: this studio runs on its own data the same way, pulled with the same tools, read back in plain words, turned into the next move. We do not hide the dashboard. The whole thing was built so you could watch the decisions, not just the output. The tools are free. The discipline is the part. If you cannot read your own machine, you do not own it. See how we read ours at office.temerarii.xyz Keywords: business intelligence for small business, MCP data analytics, read your own numbers, one chart per decision, data to action

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