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-Tuekind longformweek W46date 2026-11-17campaign longform-youtubepillar emerging_techbeat asset videoduration 141.2sground 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-W46-Tue good|bad)
⚠ 2 flag(s) — not yet ship-ready: dead_airgeneric_scene · 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 · 141.2s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–21.6sspatial-parallaxicon·liquid-chrome♪ bed_in
A publicist is not a megaphone. A good one is a matchmaker who knows exactly which outlet wants which story on which day. Today I will show you how to run that matchmaking with an AI agent, so a one person shop can do what a firm charges a retainer for. This is access into advantage, the booking version.
on-screen: What a publicist actually does
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→What a publicist actually does
2s2
matches intent
NumberedList
template
teach21.6–38.6skinetic-buildicon·wireframe♪ node_lock
First. Have the agent scrape podcasts, newsletters, and shows in your field with Apify, capturing audience size, topic, and how to submit a guest. Drop it all into Airtable through its MCP. You now own a media database instead of renting one from an expensive directory.
on-screen: Build a media database
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→Build a media databasecurate items, nodes
3s3
matches intent
ChecklistCard
template
teach38.6–58.8skinetic-buildicon·wireframe♪ node_lock
Second. Tell the model to score each outlet by how close its usual topics sit to your actual story, not by how big it is. A small show that covers your exact niche beats a giant one that will never mention you. The agent sorts the table so your best ten rise to the top.
on-screen: Rank by fit, not by reach
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→Rank by fit, not by reachcurate items, nodes
4s4
matches intent
WireframeMock
template
teach58.8–76.8skinetic-buildicon·wireframe♪ node_lock
Third. For each of those ten, have the model read three of their recent episodes and write a guest pitch that names a segment they would actually run. Not a template with the name swapped. A real angle, built from their own back catalog. You approve or you cut.
on-screen: Tailor one pitch per outlet
expected on screen: black ground · a WireframeMock panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id WireframeMockvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Tailor one pitch per outletcurate nodes
5s5
matches intent
StackTrace
template
teach76.8–94.1skinetic-buildicon·wireframe♪ node_lock
Fourth. Once a booking lands, ask the agent to turn your method into five plain talking points an eleven year old could follow. No jargon. You walk onto the show able to teach, not pitch, which is the only thing that makes a host invite you back.
on-screen: Prep the talking points
expected on screen: black ground · a StackTrace panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StackTracevisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Prep the talking pointscurate errMsg, errType, fix, frames, nodes
6s6
matches intent
PipelineMap
template
teach94.1–114.6skinetic-buildicon·wireframe♪ node_lock
The honest proof. We test this by pointing it at our own studio before any client. The media table, the fit scores, the tailored pitches, all built from the same source file that renders this very video. We are our own first publicist, in public, so you can copy the method without paying for the mystery.
on-screen: We booked ourselves first
expected on screen: black ground · a PipelineMap panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id PipelineMapvisual node-graphshape coneground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→We booked ourselves firstcurate nodes, stages
7s7
matches intent
StatScoreboard
template
proof114.6–136.2sreceipts-counticon·wireframe♪ node_lock
So the publicist move is four steps. Build the database. Rank by fit. Tailor every pitch. Prep to teach. Let the agent carry the scraping and the sorting while you carry the conversation. Watch the whole thing run at office dot temerarii dot xyz, then build your own media table this week and find the ten that actually fit.
on-screen: See it live at office.temerarii.xyz
expected on screen: black ground · a StatScoreboard panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StatScoreboardvisual receiptsshape coneground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→See it live at office.temerarii.xyzcurate pillar, stats, statsLabels
8s8
first render · fix pending
shared field
signature-3ddead_airgeneric_scene
resolve136.2–141.2scoalescenceicon·liquid-chrome♪ bed_out
Emerging tech: what's next, tested in public
on-screen: Chapter 7
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→Chapter 7

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)

youtubeBe Your Own Publicist: Build a Media Database, Rank by Fit, and Pitch to Teach A publicist is not a megaphone. A good one is a matchmaker who knows which outlet wants which story. In this video we show how to run that matchmaking with an agent, so a one-person shop can do what a firm charges a retainer for. The moves: - Build a media database. Have the agent scrape podcasts, newsletters, and shows in your field with Apify, capturing audience size, topic, and how to submit a guest. Drop it all into Airtable through its MCP. You own a media database instead of renting one. - Rank by fit, not by reach. Tell the model to score each outlet by how close its usual topics sit to your actual story, not by how big it is. A small show that covers your exact niche beats a giant one that will never mention you. - Tailor one pitch per outlet. For each of your best ten, have the model read three of their recent episodes and write a guest pitch that names a segment they would actually run. Not a template with the name swapped. - Prep the talking points. Once a booking lands, ask the agent to turn your method into five plain talking points an eleven-year-old could follow. You walk on able to teach, not pitch. The honest proof: we test this by pointing it at our own studio before any client. The media table, the fit scores, the tailored pitches, all built from the same source file that renders this video. We are our own first publicist, in public. The takeaway: build the database, rank by fit, tailor every pitch, prep to teach. Let the agent carry the scraping and sorting while you carry the conversation. Build your own media table this week. See it at office.temerarii.xyz. Keywords: publicist, podcast pitching, media database, Apify, Airtable, MCP.

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