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-W38-Tuekind longformweek W38date 2026-09-22campaign longform-youtubepillar strategic_relationsbeat asset videoduration 121.1sground redscenes 6

Checklist the per-video bar — engine/sim

98.0/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review longform-W38-Tue good|bad)
⚠ 1 flag(s) — not yet ship-ready: copy_generic · 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 · 121.1s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–19.8sspatial-parallaxicon·liquid-chrome♪ bed_in
Today is email, the cheapest line you own and the most wasted. Stop guessing, start printing applies hard here. By the end you will know how to let a model write, segment, and time your emails from your own data, so each send has a reason instead of going out because it is Tuesday.
on-screen: Email that earns its send
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→Email that earns its send
2s2
matches intent
NumberedList
template
teach19.8–41.1skinetic-buildicon·white-knockout♪ node_lock
First, split your list by behavior, not by hope. Pull your contacts and their actions from your tool, something like Resend or your shop's API, then have the model sort them: bought once, never bought, abandoned a cart. Three plain buckets. A model is fast at this. Now every email can speak to people where they actually are.
on-screen: Group by what they did
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→Group by what they didcurate items, nodes
3s3
matches intent
ChecklistCard
template
teach41.1–63.400000000000006skinetic-buildicon·liquid-chrome♪ node_lock
Hand the agent your past winners and your product facts, then ask it to draft the next email for one bucket. The trick is to feed it your own voice and real details, not a blank prompt. It writes the subject, the body, and three subject-line options. You edit for ten minutes instead of staring at a cursor for an hour.
on-screen: Let it draft from real lines
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→Let it draft from real linescurate items, nodes
4s4
matches intent
NodeGraphCard
template
teach63.4–85.4skinetic-buildicon·white-knockout♪ node_lock
Now stop sending by calendar and start sending by action. Set a simple trigger: cart abandoned, wait an hour, the agent sends the matching draft. Booking finished, send the follow-up. The model watches the event stream and fires the right note at the right minute. That is the email that pays, the one tied to something the person just did.
on-screen: Trigger on the action
expected on screen: red ground · a NodeGraphCard panel over a dimmed Signal Field · Nexus leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id NodeGraphCardvisual node-graphshape tetraground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Trigger on the actioncurate hub, nodes
5s5
matches intent
ComparisonTable
template
proof85.4–104.5sreceipts-counticon·liquid-chrome♪ node_lock
We run our own list this way. The studio's updates fire off the same source file the whole calendar comes from, so when a piece ships, the note about it writes and sends itself. No intern remembering on Friday. You can watch the studio run in public at office.temerarii.xyz, emails and all.
on-screen: Our calendar emails itself
expected on screen: red ground · a ComparisonTable panel over a dimmed Signal Field · Nexus leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id ComparisonTablevisual receiptsshape tetraground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Our calendar emails itselfcurate colA, colB, rows, statsLabels
6s6
matches intent
shared field
signature-3d
resolve104.5–121.1scoalescenceicon·liquid-chrome♪ bed_out
So: split by behavior, draft in your own voice with a model, and trigger on the action instead of the calendar. Each send earns its place. The full loop is live at office.temerarii.xyz. Set one trigger this week, the abandoned cart, and let it run.
on-screen: Send by reason, not date
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→Send by reason, not date

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)

youtubeLet a model write, segment, and time your email from your own data Email is the cheapest line you own and the most wasted. This is how to make each send have a reason instead of going out because it is Tuesday. The method: - Group by what they did, not by hope. Pull contacts and their actions from your tool, something like Resend or your shop's API, then have the model sort them: bought once, never bought, abandoned a cart. Three plain buckets, fast for a model. - Let it draft from real lines. Hand the agent your past winners and your product facts, then ask it to draft the next email for one bucket. Feed it your own voice and real details, not a blank prompt. You edit for ten minutes instead of staring for an hour. - Trigger on the action, not the calendar. Cart abandoned, wait an hour, the agent sends the matching draft. Booking finished, send the follow-up. The email that pays is the one tied to something the person just did. The honest proof: we run our own list this way. The studio's updates fire off the same source file the whole calendar comes from, so when a piece ships, the note about it writes and sends itself. No intern remembering on Friday. Split by behavior, draft in your own voice with a model, and trigger on the action. Set one trigger this week, the abandoned cart, and let it run. The full loop is at office.temerarii.xyz. Keywords: email marketing, list segmentation, behavioral triggers, Resend API, automated email.

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