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-W46-Thukind longformweek W46date 2026-11-19campaign longform-youtubepillar multimediabeat asset videoduration 126.5sground whitescenes 7

Checklist the per-video bar — engine/sim

98.2/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review longform-W46-Thu good|bad)
⚠ 1 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 7 scenes · 126.5s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–20.5sspatial-parallaxicon·wireframe♪ bed_in
Event coordination is where most money quietly leaks. You spend on a booth or a dinner and never know if it worked. Today I show you how an AI agent plans an event around a real goal and tracks who showed up, so this week's idea, access into advantage, has numbers behind it instead of vibes.
on-screen: Events that pay for themselves
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground whitetreatment wireframemotion spatial-parallaxpower summoninstrument summon→Events that pay for themselves
2s2
matches intent
NumberedList
template
teach20.5–41.4skinetic-buildicon·wireframe♪ node_lock
First. Before you book a room, tell the agent who you want in it. Have it scrape the local companies and roles you are targeting and build the guest list in Airtable first. The event exists to get those specific people together. The model builds the list, the list shapes the event, not the other way around.
on-screen: Plan backward from the guest list
expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape octaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Plan backward from the guest listcurate items, nodes
3s3
matches intent
ChecklistCard
template
teach41.4–60.2skinetic-buildicon·wireframe♪ node_lock
Second. Wire the agent into Gmail and Google Calendar through their MCP servers. It drafts a personal invite for each name, sends the calendar hold, and schedules two reminders so nobody forgets. You approve the wording once. The agent runs the chase so you are not copy pasting invites at midnight.
on-screen: Automate the invite and the reminder
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape octaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Automate the invite and the remindercurate items, nodes
4s4
matches intent
ProcessFlow
template
teach60.2–79.0skinetic-buildicon·wireframe♪ node_lock
Third. The day after, have the model turn your attendee notes into a follow-up for each person that mentions what you actually talked about. A real detail, not dear valued guest. The agent reads your notes and drafts twenty warm follow-ups in the time it took you to find your car.
on-screen: Capture the room, then follow up
expected on screen: white ground · a ProcessFlow panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ProcessFlowvisual node-graphshape octaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Capture the room, then follow upcurate nodes, steps
5s5
matches intent
FlowSchematic
template
teach79.0–97.4skinetic-buildicon·wireframe♪ node_lock
Honest proof. We plan our own gatherings with this loop, guest list first, follow-ups automated, all logged in the same Airtable that the source file behind this video reads from. No fabricated turnout. Just the method, run on The Big T-M, in the open, so you can lift it whole.
on-screen: We run our own events this way
expected on screen: white ground · a FlowSchematic panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id FlowSchematicvisual node-graphshape octaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→We run our own events this waycurate nodes, stages
6s6
first render · fix pending
KpiGrid
templatecustom_element_dup
proof97.4–121.5sreceipts-counticon·wireframe♪ node_lock
Wait, that was the proof, here is the takeaway. Plan backward from the guest list. Automate the invites and reminders. Capture the room and follow up with real detail. Let the agent carry the logistics while you carry the conversation. The studio is live at office dot temerarii dot xyz. Pick the ten people you want in a room and let the model build the list.
on-screen: Plan it at office.temerarii.xyz
expected on screen: white ground · a KpiGrid panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id KpiGridvisual receiptsshape octaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Plan it at office.temerarii.xyzcurate kpis, statsLabels
7s7
matches intent
shared field
signature-3d
resolve121.5–126.5scoalescenceicon·wireframe♪ bed_out
Creative workflows: the give-it-away method, end to end
on-screen: Chapter 6
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground whitetreatment wireframemotion coalescencepower coalescenceinstrument coalescence→Chapter 6

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)

youtubePlan an Event Backward From the Guest List So It Actually Feeds Your Pipeline Events are where money quietly leaks. You spend on a booth or a dinner and never know if it worked. In this video we show how an agent plans an event around a real goal and tracks who showed up. The moves: - Plan backward from the guest list. Before you book a room, tell the agent who you want in it. Have it scrape the local companies and roles you are targeting and build the guest list in Airtable first. The list shapes the event, not the other way around. - Automate the invite and the reminder. Wire the agent into Gmail and Google Calendar through their MCP servers. It drafts a personal invite for each name, sends the calendar hold, and schedules two reminders. You approve the wording once. - Capture the room, then follow up. The day after, have the model turn your attendee notes into a follow-up for each person that mentions what you actually talked about. A real detail, not dear valued guest. The honest proof: we plan our own gatherings with this loop, guest list first, follow-ups automated, all logged in the same Airtable that the source file behind this video reads from. No fabricated turnout, just the method run in the open. The takeaway: plan backward from the guest list, automate the invites and reminders, capture the room and follow up with real detail. Let the agent carry the logistics while you carry the conversation. Pick the ten people you want in a room and let the model build the list. See it at office.temerarii.xyz. Keywords: event planning, Airtable, Gmail, Google Calendar, MCP, follow-up automation.

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