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-W48-Thukind longformweek W48date 2026-12-03campaign longform-youtubepillar strategic_relationsbeat —asset videoduration 145.4sground redscenes 6

Checklist the per-video bar — engine/sim

87.1/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review longform-W48-Thu good|bad)
⚠ 2 flag(s) — not yet ship-ready: dup_sequence_across_assetsdup_set_across_assets · 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 6 scenes · 145.4s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		open0–21.6sspatial-parallaxicon·liquid-chrome♪ bed_in
The operating layer is also about seeing clearly. Today is business intelligence, which is a fancy name for a plain idea: knowing your real numbers without a week of spreadsheet wrestling. You will learn how to put one agent between you and your data so you can ask a question in plain words and get a straight answer back.
on-screen: See your numbers, finally
expected on screen: red ground · tetra hero in the shared Signal Field · Nexus leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape tetraground redtreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→See your numbers, finally
2s2
matches intent
NumberedList
template		teach21.6–45.0skinetic-buildicon·white-knockout♪ node_lock
Step one. Connect the agent to where your numbers actually live, your database or your Google Sheets, through an MCP server. This is the bridge. Once it is wired, the model can read your sales, your sign-ups, your costs, directly. You stop exporting files and emailing them around. The data sits in one place and the agent reaches in and reads it on demand.
on-screen: Wire the agent to your data
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Nexus leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape tetraground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Wire the agent to your datacurate items, nodes
3s3
matches intent
ChecklistCard
template		teach45.0–70.9skinetic-buildicon·liquid-chrome♪ node_lock
Step two. Now ask a real question out loud: how many orders came from each state last month? The agent turns your plain question into SQL, the query language databases speak, runs it, and hands back the answer. You never learned SQL and you do not need to. The big T-M lets the model write the query and shows you the query too, so you can check it told the truth.
on-screen: Ask in plain words, get real SQL
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Nexus leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape tetraground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Ask in plain words, get real SQLcurate items, nodes
4s4
matches intent
BlueprintGrid
template		teach70.9–96.80000000000001skinetic-buildicon·white-knockout♪ node_lock
Step three. Numbers in a row are hard to feel. Tell the agent to turn the answer into a simple chart and save it as an image. It writes the small bit of code, runs it, and you get a picture you can drop in a meeting. The point of business intelligence is not more data. It is seeing the shape of it fast enough to act before the moment passes.
on-screen: Make it draw the chart for you
expected on screen: red ground · a BlueprintGrid panel over a dimmed Signal Field · Nexus leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id BlueprintGridvisual node-graphshape tetraground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Make it draw the chart for youcurate nodes, rows
5s5
matches intent
LegacyCard
template		proof96.8–123.1sreceipts-counticon·liquid-chrome♪ node_lock
Our proof sits in front of you. This whole calendar tracks its own state, what is built, what is clean, what still needs work, and an agent reads that and tells us the shape of it in plain words. We did not buy a dashboard. We wired the agent to our own data and asked. The honest result is we always know where we stand without anyone building a report by hand.
on-screen: This calendar reports on itself
expected on screen: red ground · a LegacyCard panel over a dimmed Signal Field · Nexus leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id LegacyCardvisual receiptsshape tetraground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→This calendar reports on itselfcurate statsLabels
6s6
matches intent
shared field
signature-3d		resolve123.1–145.4scoalescenceicon·liquid-chrome♪ bed_out
So business intelligence is just removing the middleman between you and your own truth. Wire the agent to your data, ask in plain words, let it write the query and the chart. Start with the one number you keep guessing at. See how we read our own numbers at office dot temerarii dot xyz, then go ask your data a question.
on-screen: See it run at office.temerarii.xyz
expected on screen: red ground · tetra hero in the shared Signal Field · Nexus leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape tetraground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→See it run 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 in Plain Words: Ask Your Data a Question, Get a Straight Answer The operating layer is also about seeing clearly. Business intelligence is a fancy name for a plain idea: knowing your real numbers without a week of spreadsheet wrestling. In this video we put one agent between you and your data so you can ask a question in plain words and get a straight answer. The moves: - Wire the agent to your data. Connect the agent to where your numbers actually live, your database or your Google Sheets, through an MCP server. Once it is wired, the model reads your sales, sign-ups, and costs directly. You stop exporting files and emailing them around. - Ask in plain words, get real SQL. Ask a real question out loud: how many orders came from each state last month. The agent turns your plain question into SQL, the query language databases speak, runs it, and hands back the answer. It shows you the query too, so you can check it told the truth. - Make it draw the chart for you. Numbers in a row are hard to feel. Tell the agent to turn the answer into a simple chart and save it as an image. It writes the small bit of code and you get a picture you can drop in a meeting. The honest proof: this whole calendar tracks its own state, what is built, what is clean, what still needs work, and an agent reads that and tells us the shape of it in plain words. We did not buy a dashboard. We wired the agent to our own data and asked. We always know where we stand without anyone building a report by hand. The takeaway: wire the agent to your data, ask in plain words, let it write the query and the chart. Start with the one number you keep guessing at. See how we read our own numbers at office.temerarii.xyz, then go ask your data a question. Keywords: business intelligence, SQL, data analysis, Google Sheets, MCP, AI agent.

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

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