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-brand-creativekind topicweek date campaign brand-pillarpillar brandbeat asset videoduration 57.3sground blackscenes 9

Checklist the per-video bar — engine/sim

94.9/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review topic-brand-creative 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 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 9 scenes · 57.3s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–5.5sspatial-parallaxicon·white-knockout♪ —
Every brand starts as a single idea, and getting that idea right is harder than any logo.
on-screen: A brand starts as one idea
expected on screen: black ground · icosa hero in the shared Signal Field · Signum leads · node-graph · spatial-parallax · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape icosaground blacktreatment white-knockoutmotion spatial-parallaxpower summoninstrument summon→three-mark
2s2
matches intent
LogStream
template
legacy5.5–11.0scrossfade-8ficon·ember-fill♪ —
The old way was weeks of mood boards and meetings before anyone could even see the idea.
on-screen: Old way: weeks of mood boards
expected on screen: black ground · a LogStream panel over a dimmed Signal Field · Signum leads · crossfade-8f · icon·ember-fill logo · caption bottom-left
spec (the prompt): comp_id LogStreamshape icosaground blacktreatment ember-fillmotion crossfade-8fpower morphinstrument decay→three-symboliccurate rows
3s3
matches intent
NumberedList
template
teach11.0–18.0skinetic-buildicon·wireframe♪ —
Step one, we turn the brief into sharp prompts, naming the feeling, the audience, and the world it lives in.
on-screen: Step 1: turn the brief into prompts
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape icosaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-panelcurate items, nodes
4s4
matches intent
ChecklistCard
template
teach18.0–26.1skinetic-buildicon·white-knockout♪ —
Step two, an image model spins up twelve visual directions in an hour, so we react to real pictures, not adjectives.
on-screen: Step 2: generate twelve directions fast
expected on screen: black ground · a ChecklistCard panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape icosaground blacktreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→three-diagramcurate items, nodes
5s5
matches intent
BlueprintGrid
template
teach26.1–32.300000000000004skinetic-buildicon·liquid-chrome♪ —
Step three, we cut twelve down to three and write the reason each one earns its place, in plain language.
on-screen: Step 3
expected on screen: black ground · a BlueprintGrid panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left
spec (the prompt): comp_id BlueprintGridvisual node-graphshape icosaground blacktreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→html-in-canvas-codecurate nodes, rows
6s6
matches intent
CodeWindow
template
teach32.3–39.9skinetic-buildicon·ember-fill♪ —
Step four, once a direction is picked we extract its rules, color, shape, motion, into a system anyone can follow.
on-screen: Step 4
expected on screen: black ground · a CodeWindow panel over a dimmed Signal Field · Signum leads · node-graph · kinetic-build · icon·ember-fill logo · caption bottom-left
spec (the prompt): comp_id CodeWindowvisual node-graphshape icosaground blacktreatment ember-fillmotion kinetic-buildpower morphinstrument morph+laser→three-flowcurate codeLines, nodes, windowTitle
7s7
matches intent
ComparisonTable
template
proof39.9–45.6sreceipts-counticon·wireframe♪ —
We show the timeline openly, brief in the morning, three real concepts by end of day.
on-screen: Receipts: brief to concept in a day
expected on screen: black ground · a ComparisonTable panel over a dimmed Signal Field · Signum leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ComparisonTablevisual receiptsshape icosaground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→html-in-canvas-receiptscurate colA, colB, rows, statsLabels
8s8
matches intent
shared field
signature-3d
futurist45.6–51.800000000000004sspatial-parallaxicon·white-knockout♪ —
Soon the concept arrives in 3D, a world you can rotate and step into before a line is finalized.
on-screen: Next: concepts you can walk around
expected on screen: black ground · icosa hero in the shared Signal Field · Signum leads · spatial-parallax · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldshape icosaground blacktreatment white-knockoutmotion spatial-parallaxpower spatial-parallaxinstrument laser-fire→three-forward
9s9
matches intent
shared field
signature-3d
resolve51.8–57.3scoalescenceicon·white-knockout♪ swell
Take your next brief, generate three directions before the first meeting, and walk in with pictures.
on-screen: Prompt three directions from your brief
expected on screen: black ground · icosa hero in the shared Signal Field · Signum leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape icosaground 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)

tiktokEvery brand starts as one idea, and getting that idea right is harder than any logo. AI-assisted. The old way was weeks of mood boards before anyone could see it. The new way: turn the brief into sharp prompts naming the feeling, audience, and world. Let an image model spin up twelve directions in an hour, so you react to real pictures, not adjectives. Cut twelve to three, write why each earns its place, then extract the winner's rules into a system anyone can follow. Brief in the morning, three real concepts by end of day. temerarii.com.
instagramEvery brand starts as one idea. Getting it right is harder than any logo. Turn the brief into prompts. Generate twelve directions in an hour. Cut to three. Write why each earns it. Extract the winner's rules. Brief in the morning. Three concepts by end of day. #temerarii #creativedirection #branding #aitools #designprocess
linkedinEvery brand starts as a single idea, and getting that idea right is harder than any logo. The old way was weeks of mood boards before anyone could even see it. Here is how we get to three real concepts in a day. 1. Turn the brief into sharp prompts, naming the feeling, the audience, and the world it lives in. 2. Let an image model spin up twelve visual directions in an hour, so you react to real pictures, not adjectives. 3. Cut twelve down to three and write, in plain language, why each one earns its place. 4. Once a direction is picked, extract its rules, color, shape, motion, into a system anyone can follow. The timeline, shown openly: brief in the morning, three real concepts by end of day. Take your next brief, generate three directions before the first meeting, and walk in with pictures. temerarii.com
xEvery brand starts as one idea. Getting it right is harder than any logo. Turn the brief into prompts. Generate 12 directions in an hour. Cut to 3, write why each earns it. Extract the winner's rules. Brief AM, three concepts by EOD. temerarii.com
facebookEvery brand starts as a single idea, and getting that idea right is harder than any logo. The old way was weeks of mood boards. The new way: turn the brief into sharp prompts, let an image model spin up twelve directions in an hour, cut to three, write why each earns its place, then extract the winner's rules into a system anyone can follow. Brief in the morning, three real concepts by end of day. Generate your three directions before the first meeting: temerarii.com
threadsEvery brand starts as one idea, and getting it right is harder than any logo. Turn the brief into sharp prompts. Let an image model spin up twelve directions in an hour, so you react to real pictures, not adjectives. Cut to three, write why each earns its place, then extract the winner's rules. Brief in the morning, three concepts by end of day. temerarii.com
pinterestCreative direction with AI: turn a brand brief into sharp prompts, generate twelve visual directions in an hour, cut to three with a written reason for each, then extract the winner's rules into a system. Go from brief to three real concepts in a single day. Design process, branding workflow, image models.
blueskyEvery brand starts as one idea. Getting it right is harder than any logo. Turn the brief into prompts. Generate twelve directions in an hour. Cut to three, write why each earns it. Extract the winner's rules. Brief in the morning, three concepts by end of day. temerarii.com
youtubeBrief to Three Real Concepts in a Day: AI Creative Direction Every brand starts as a single idea, and getting that idea right is harder than any logo. The old way was weeks of mood boards and meetings before anyone could even see the idea. Here is the full method. 1. Turn the brief into sharp prompts, naming the feeling, the audience, and the world it lives in. 2. Let an image model spin up twelve visual directions in an hour, so you react to real pictures, not adjectives. 3. Cut twelve down to three and write, in plain language, why each one earns its place. 4. Once a direction is picked, extract its rules, color, shape, motion, into a system anyone can follow. The timeline, shown openly: brief in the morning, three real concepts by end of day. What is next is concepts that arrive in 3D, a world you can rotate and step into before a line is finalized. Take your next brief, generate three directions before the first meeting, and walk in with pictures. More at temerarii.com

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