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-W24-Fri-3kind threadweek W24date 2026-06-19campaign thread · Fripillar emerging_techbeat Friasset videoduration 55.2sground whitescenes 9

Checklist the per-video bar — engine/sim

96.0/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review social-W24-Fri-3 good|bad)
⚠ 2 flag(s) — not yet ship-ready: copy_generictoo_complex · 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 · 55.2s · 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·ember-fill♪ bed_in
Most connected devices collect a flood of data nobody ever looks at.
on-screen: Smart devices, dumb data
expected on screen: white ground · cone hero in the shared Signal Field · Augur leads · node-graph · spatial-parallax · icon·ember-fill logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape coneground whitetreatment ember-fillmotion spatial-parallaxpower summoninstrument summon→Smart devices, dumb data
2s2
matches intent
shared field
signature-3d		hook5.0–10.9skinetic-buildicon·wireframe♪ node_lock
Here is how The Big T-M turns that sensor flood into something that actually acts.
on-screen: How AI makes the data act
expected on screen: white ground · cone hero in the shared Signal Field · Augur leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual markshape coneground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→How AI makes the data act
3s3
matches intent
NumberedList
template		teach10.9–17.5skinetic-buildicon·wireframe♪ node_lock
Define what a normal reading looks like first, so the device knows when something is genuinely wrong.
on-screen: Decide what each reading means
expected on screen: white 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 whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Decide what each reading meanscurate items, nodes
4s4
matches intent
ComparisonTable
template		proof17.5–24.8sreceipts-counticon·wireframe♪ node_lock
The proof: a model that learns the normal hum can warn you a part is failing before it fails.
on-screen: Catch the failure before it breaks
expected on screen: white ground · a ComparisonTable panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ComparisonTablevisual receiptsshape coneground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Catch the failure before it breakscurate colA, colB, rows, statsLabels
5s5
matches intent
JsonDiff
template		diff24.8–30.0scrossfade-8ficon·wireframe♪ node_lock
The old way logged everything to a dashboard somebody checked next quarter, maybe.
on-screen: Old way: read the dashboard later
expected on screen: white ground · a JsonDiff panel over a dimmed Signal Field · Augur leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id JsonDiffvisual codeshape coneground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Old way: read the dashboard latercurate codeLines, fileName, lines
6s6
matches intent
ChecklistCard
template		teach30.0–37.0skinetic-buildicon·wireframe♪ node_lock
Now you let the device decide on the spot and send only the alert, not the whole firehose.
on-screen: Decide at the edge, send only alerts
expected on screen: white 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 whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Decide at the edge, send only alertscurate items, nodes
7s7
matches intent
KpiGrid
template		proof37.0–42.9sreceipts-counticon·wireframe♪ node_lock
The receipt is speed: less data shipped means a faster response and a smaller bill.
on-screen: Less data moved, faster action
expected on screen: white 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 whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Less data moved, faster actioncurate kpis, statsLabels
8s8
matches intent
CheatSheet
template		step42.9–50.199999999999996skinetic-buildicon·wireframe♪ node_lock
Start with the one sensor tied to a real cost, and prove the savings before you wire the building.
on-screen: Start with one sensor that matters
expected on screen: white ground · a CheatSheet panel over a dimmed Signal Field · Augur leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id CheatSheetvisual pipelineshape coneground whitetreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Start with one sensor that matterscurate points, stages, steps, uses
9s9
matches intent
shared field
signature-3d		resolve50.2–55.2scoalescenceicon·ember-fill♪ bed_out
Build sensors that decide, not ones that only count.
on-screen: Sensors that decide, not just count
expected on screen: white ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·ember-fill logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground whitetreatment ember-fillmotion coalescencepower coalescenceinstrument coalescence→Sensors that decide, not just count

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)

tiktokSmart devices collect a flood of data nobody reads. AI-assisted: teach a model the NORMAL hum so it warns you a part is failing before it fails, decide at the edge, and send only the alert, not the firehose. Method below.
instagramSmart devices, dumb data. Learn the normal hum. Warn before it breaks. Decide at the edge. Send alerts, not the firehose. #iot #internetofthings #ai #emergingtech #temerarii
linkedinMost connected devices collect a flood of data nobody ever looks at. How we make IoT data act: define what a normal reading looks like so the device knows when something is genuinely wrong, train a model on that normal hum so it warns you a part is failing before it fails, and let the device decide on the spot and send only the alert, not the whole firehose. Takeaway: start with the one sensor tied to a real cost, prove the savings, then wire the rest.
xSmart devices collect a flood of data nobody reads. Learn the normal hum → warn before it breaks → decide at the edge → send alerts, not the firehose. Sensors that decide, not count. temerarii.com
facebookMost connected devices collect a flood of data nobody ever looks at. Here's how we make it act: define what a normal reading looks like, train a model on that normal hum so it warns you a part is failing before it fails, and let the device decide on the spot and send only the alert. Start with the one sensor tied to a real cost. Want the IoT approach? It's on the site.
threadsSmart devices collect a flood of data nobody reads. Learn the normal hum, warn before it breaks, decide at the edge, send alerts not the firehose. Build sensors that decide, not count.
pinterestInternet of Things with AI: how to define normal readings, predict failures from sensor data, decide at the edge, and send alerts instead of raw data. Plain-language IoT and predictive maintenance guide for businesses.
blueskySmart devices collect a flood of data nobody reads. Learn the normal hum, warn before it breaks, decide at the edge, send alerts not the firehose. temerarii.com
youtubeInternet Of Things: Make The Data Act, Not Just Pile Up Most connected devices collect a flood of data nobody ever looks at. This walkthrough shows how we make it useful: define what a normal reading looks like, train a model on that normal hum so it warns you a part is failing before it fails, and let the device decide on the spot and send only the alert, not the whole firehose. Start with the one sensor tied to a real cost. AI-assisted production. Give-it-away method from The Big T-M. Chapters: dumb data · learn the normal · warn early · decide at the edge · start with one sensor.

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

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