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 topic-x-the-machinekind topicweek date campaign it-dev-pillarpillar it_devbeat asset videoduration 134.1sground blackscenes 19

Checklist the per-video bar — engine/sim

96.3/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review topic-x-the-machine good|bad)
⚠ 1 flag(s) — not yet ship-ready: too_complex · see docs/strategy/VIDEO-CHECKLIST.md

Composition comp · template family · expected output

composition SceneReelfamily / template SceneReel
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
▶ open rendered mp4
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.

Composition layer × scene 19 scenes · 134.1s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–7.9sspatial-parallaxicon·white-knockout♪ —
This whole channel runs on a machine. One topic goes in, finished posts come out everywhere, and here's the actual build.
on-screen: One brief, all platforms
expected on screen: black ground · box hero in the shared Signal Field · Faber leads · node-graph · spatial-parallax · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape boxground blacktreatment white-knockoutmotion spatial-parallaxpower summoninstrument summon→three-mark
2s2
matches intent
CodeWindow
template
legacy7.9–15.3scrossfade-8ficon·wireframe♪ —
The old way needed a researcher, a writer, a voice talent, an editor, and a poster. Five people for one daily post.
on-screen: Old way: a team of five
expected on screen: black ground · a CodeWindow panel over a dimmed Signal Field · Faber leads · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id CodeWindowshape boxground blacktreatment wireframemotion crossfade-8fpower morphinstrument decay→three-symboliccurate codeLines, windowTitle
3s3
matches intent
NumberedList
template
teach15.3–23.5skinetic-buildicon·wireframe♪ —
It starts with research: several scrapers and a search tool fire at once, pulling what's actually trending, not what we guessed.
on-screen: Step 1: research in parallel
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate items, nodes
4s4
matches intent
ChecklistCard
template
teach23.5–29.9skinetic-buildicon·wireframe♪ —
Then we diagram the choose step: the model reads every source and picks the one angle worth a video today.
on-screen: Sources -> pick the angle
expected on screen: black ground · a ChecklistCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate items, nodes
5s5
matches intent
StackTrace
template
teach29.9–36.9skinetic-buildicon·wireframe♪ —
The script is written to a fixed voice and structure, so every piece sounds like us and teaches a real method, never
on-screen: Script from a locked voice
expected on screen: black ground · a StackTrace panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StackTracevisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate errMsg, errType, fix, frames, nodes
6s6
matches intent
ProcessFlow
template
teach36.9–44.1skinetic-buildicon·wireframe♪ —
It flows downhill: the script becomes a voiceover, the voiceover drives a video render, the render gets captions.
on-screen: Script -> voice -> render
expected on screen: black ground · a ProcessFlow panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ProcessFlowvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate nodes, steps
7s7
matches intent
FlowSchematic
template
teach44.1–51.800000000000004skinetic-buildicon·wireframe♪ —
The voice is one API call to ElevenLabs with our cloned voice, so narration is consistent and costs cents, not a session.
on-screen: Voiceover from one line
expected on screen: black ground · a FlowSchematic panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id FlowSchematicvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate nodes, stages
8s8
matches intent
AnnotatedDiagram
template
teach51.8–59.0skinetic-buildicon·wireframe♪ —
We diagram the video itself: Remotion builds it scene by scene from a plan, so the look is code, not a shoot.
on-screen: Scenes built, not filmed
expected on screen: black ground · a AnnotatedDiagram panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id AnnotatedDiagramvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate callouts, nodes
9s9
matches intent
SchematicCard
template
teach59.0–66.2skinetic-buildicon·wireframe♪ —
The render is a single command against a Remotion composition, the same way you build software, repeatable every time.
on-screen: Render the composition
expected on screen: black ground · a SchematicCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id SchematicCardvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate nodes
10s10
matches intent
StepFlow
template
teach66.2–73.0skinetic-buildicon·wireframe♪ —
From one master, the flow produces every aspect ratio and length each platform wants, automatically.
on-screen: One master -> many cuts
expected on screen: black ground · a StepFlow panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StepFlowvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate nodes, steps
11s11
matches intent
BuildLog
template
teach73.0–79.8skinetic-buildicon·wireframe♪ —
Captions are generated from the same script and burned to match each platform's safe zones, so nothing gets cropped
on-screen: Captions burned per platform
expected on screen: black ground · a BuildLog panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id BuildLogvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate lines, nodes
12s12
matches intent
LegacyCard
template
teach79.8–86.89999999999999skinetic-buildicon·wireframe♪ —
We diagram distribution: one call posts to every account, logs the result, and schedules the next slot.
on-screen: Post -> log -> schedule
expected on screen: black ground · a LegacyCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id LegacyCardvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate nodes
13s13
matches intent
NodeGraphCard
template
teach86.9–93.7skinetic-buildicon·wireframe♪ —
Posting is one call to a distribution tool that fans out to sixteen accounts across both profiles at once.
on-screen: Sixteen accounts, one call
expected on screen: black ground · a NodeGraphCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NodeGraphCardvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate hub, nodes
14s14
matches intent
DiffCard
template
teach93.7–101.0skinetic-buildicon·wireframe♪ —
It flows to a log: every asset records its topic, render, and post status in a database we can audit later.
on-screen: Every run logged to a base
expected on screen: black ground · a DiffCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id DiffCardvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate lines, nodes
15s15
matches intent
TerminalRun
template
teach101.0–107.6skinetic-buildicon·wireframe♪ —
Scaling output doesn't mean hiring, it means feeding the machine more topics. The pipeline doesn't get tired.
on-screen: Add a topic, not a worker
expected on screen: black ground · a TerminalRun panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id TerminalRunvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate nodes
16s16
matches intent
WireframeMock
template
teach107.6–115.5skinetic-buildicon·wireframe♪ —
We map the full loop on one board: research, curate, script, voice, render, post, log, then back to research.
on-screen: The whole loop, one diagram
expected on screen: black ground · a WireframeMock panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id WireframeMockvisual node-graphshape boxground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate nodes
17s17
matches intent
StatScoreboard
template
proof115.5–122.0sreceipts-counticon·wireframe♪ —
What took five people now runs as one pipeline, producing more pieces a day than that team shipped in a week.
on-screen: A team-of-five, in software
expected on screen: black ground · a StatScoreboard panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StatScoreboardvisual receiptsshape boxground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→html-in-canvas-receiptscurate pillar, stats, statsLabels
18s18
matches intent
shared field
signature-3d
futurist122.0–127.8sspatial-parallaxicon·wireframe♪ —
Soon a brand's whole media operation is a few pipelines you tune, not a department you staff.
on-screen: Pipelines instead of headcount
expected on screen: black ground · box hero in the shared Signal Field · Faber leads · spatial-parallax · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldshape boxground blacktreatment wireframemotion spatial-parallaxpower spatial-parallaxinstrument laser-fire→three-forward
19s19
matches intent
shared field
signature-3d
resolve127.8–134.1scoalescenceicon·white-knockout♪ swell
Want a content machine like this one for your brand? We build them. Start at temerarii.xyz.
on-screen: We'll build your machine
expected on screen: black ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground blacktreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→three-coalescence

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 12 destinations

LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBlueskyEmailSMSBlog

Social captions supplemental published copy · per channel (comp_id level)

tiktokThis whole channel runs on a machine. One topic goes in, finished posts come out everywhere. Here is the actual build (AI-assisted). Several scrapers and a search tool fire at once to find what is trending. The model picks the one angle worth a video, writes the script to a fixed voice, turns it into a voiceover with one API call, and Remotion builds the video scene by scene from a plan. One master makes every aspect ratio and length, captions are burned per platform, and one call posts to sixteen accounts. Scaling means feeding more topics, not hiring. Method at temerarii.xyz.
instagramThis channel runs on a machine. One topic in, finished posts out everywhere. The build: Scrapers and search fire in parallel to find what is trending The model picks the one angle worth a video Script to a fixed voice, then a voiceover from one API call Remotion builds the video scene by scene from a plan One master makes every ratio and length One call posts to sixteen accounts Scaling means more topics, not more headcount. Method at temerarii.xyz #contentautomation #remotion #aivideo #marketing #pipeline
linkedinThis whole channel runs on a machine: one topic goes in, finished posts come out everywhere. Here is the actual build. The old way needed a researcher, a writer, a voice talent, an editor, and a poster. Five people for one daily post. The pipeline: - Several scrapers and a search tool fire in parallel to find what is actually trending - The model reads every source and picks the one angle worth a video today - The script is written to a fixed voice and structure, so every piece teaches a real method - The script becomes a voiceover with one API call to a cloned voice - Remotion builds the video scene by scene from a plan, so the look is code, not a shoot - From one master, the flow produces every aspect ratio and length each platform wants - Captions are generated from the same script and burned to match each platform's safe zones - One call posts to sixteen accounts across both profiles, and logs the result to a database Scaling output does not mean hiring; it means feeding the machine more topics. What took five people now runs as one pipeline. The method is yours. If you want a content machine built for your brand, The Big T-M does that at temerarii.xyz
xThis channel runs on a machine: one topic in, finished posts out everywhere. Scrapers find the trend, the model picks the angle, a fixed voice scripts it, Remotion renders it, one call posts to 16 accounts. Scaling means more topics, not hiring. temerarii.xyz
facebookThis whole channel runs on a machine. One topic goes in, finished posts come out everywhere, and here is the actual build. Several scrapers and a search tool fire at once to find what is trending. The model picks the one angle worth a video, writes the script to a fixed voice, and turns it into a voiceover with one API call. Remotion then builds the video scene by scene from a plan. From one master, the flow makes every aspect ratio and length, burns captions per platform, and posts to sixteen accounts with one call. Scaling output means feeding more topics, not hiring. Want a content machine like this for your brand? Start at temerarii.xyz
threadsThis channel runs on a machine. One topic in, finished posts out everywhere. Scrapers find the trend. The model picks the angle. A fixed voice scripts it, one API call voices it, Remotion renders it scene by scene. One master makes every ratio, then one call posts to sixteen accounts. Scaling means more topics, not hiring. Method at temerarii.xyz
pinterestHow to build a content machine that turns one topic into finished posts everywhere: run scrapers and search in parallel to find the trend, let an AI pick the angle, write the script to a fixed voice, generate the voiceover by API, render the video with Remotion scene by scene, make every aspect ratio from one master, burn captions per platform, and post to many accounts with one call. Scale by adding topics, not headcount. Evergreen content automation method.
blueskyOne topic in, finished posts out everywhere. The machine: scrapers find the trend, the model picks the angle, a fixed voice scripts it, one API call voices it, Remotion renders it, one call posts to 16 accounts. Add topics, not headcount. temerarii.xyz
youtubeHow We Built a Content Machine: One Topic In, Posts Out Everywhere This whole channel runs on a machine. One topic goes in, finished posts come out everywhere. This walkthrough teaches the actual build, end to end. What we cover: - Running several scrapers and a search tool in parallel to find what is actually trending - Letting the model read every source and pick the one angle worth a video today - Writing the script to a fixed voice and structure so every piece teaches a real method - Turning the script into a voiceover with one API call to a cloned voice - Building the video scene by scene with Remotion from a plan, so the look is code, not a shoot - Producing every aspect ratio and length from one master, automatically - Generating captions from the same script and burning them to match each platform's safe zones - Posting to sixteen accounts across both profiles with one call, and logging every run to a database Scaling output does not mean hiring; it means feeding the machine more topics. The pipeline does not get tired. What took five people now runs as one system. The method is yours to keep. If you want a content machine built for your brand, The Big T-M does that at temerarii.xyz AI-assisted production.

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