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 social-W33-Fri-4kind threadweek W33date 2026-08-21campaign thread · Fripillar staff_trainingbeat Friasset videoduration 68.6sground whitescenes 9

Checklist the per-video bar — engine/sim

86.6/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review social-W33-Fri-4 good|bad)
⚠ 3 flag(s) — not yet ship-ready: copy_genericdup_sequence_across_assetsdup_set_across_assets · see docs/strategy/VIDEO-CHECKLIST.md

Composition comp · template family · expected output

composition SceneReelfamily / template SignalFieldReel
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 9 scenes · 68.6s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–8.1sspatial-parallaxicon·color♪ bed_in
The plainest truth about this whole wave is that the model is a tool, not a wizard who knows your business.
on-screen: AI is a tool, not a wizard
expected on screen: white ground · knot hero in the shared Signal Field · Magister leads · node-graph · spatial-parallax · icon·color logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape knotground whitetreatment colormotion spatial-parallaxpower summoninstrument summon→AI is a tool, not a wizard
2s2
matches intent
shared field
signature-3d
hook8.1–14.7skinetic-buildicon·wireframe♪ node_lock
Early on, people typed make me money and got mush, then decided the whole thing was useless.
on-screen: The old way: expect mind-reading
expected on screen: white ground · knot hero in the shared Signal Field · Magister leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual markshape knotground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→The old way: expect mind-reading
3s3
matches intent
NumberedList
template
teach14.7–23.799999999999997skinetic-buildicon·wireframe♪ node_lock
Here is the move: tell it who to be, what you want, and the limits, the same way you would brief a new hire.
on-screen: Give it role, goal, and limits
expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Magister leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape knotground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Give it role, goal, and limitscurate items, nodes
4s4
matches intent
RankList
template
proof23.8–32.2sreceipts-counticon·wireframe♪ node_lock
Give it a real brief and it returns real work. Give it a vague wish and it hands you a vague answer.
on-screen: Clear brief in, useful work out
expected on screen: white ground · a RankList panel over a dimmed Signal Field · Magister leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id RankListvisual receiptsshape knotground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Clear brief in, useful work outcurate rows, statsLabels
5s5
matches intent
TerminalRun
template
diff32.2–38.800000000000004scrossfade-8ficon·wireframe♪ node_lock
Clever wording is not the trick. Being specific about the job is what actually changes the output.
on-screen: Specific prompts beat fancy ones
expected on screen: white ground · a TerminalRun panel over a dimmed Signal Field · Magister leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id TerminalRunvisual codeshape knotground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Specific prompts beat fancy onescurate codeLines
6s6
matches intent
ChecklistCard
template
teach38.8–46.9skinetic-buildicon·wireframe♪ node_lock
Now show it one example of what good looks like, because a model copies a pattern far better than a rule.
on-screen: Show it one good example
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Magister leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ChecklistCardvisual node-graphshape knotground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Show it one good examplecurate items, nodes
7s7
matches intent
StatScoreboard
template
proof46.9–53.9sreceipts-counticon·wireframe♪ node_lock
Paste one strong sample and the next answer matches that level, no long lecture about your standards needed.
on-screen: One example, the quality jumps
expected on screen: white ground · a StatScoreboard panel over a dimmed Signal Field · Magister leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StatScoreboardvisual receiptsshape knotground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→One example, the quality jumpscurate pillar, stats, statsLabels
8s8
matches intent
BlueprintGrid
template
step53.9–60.9skinetic-buildicon·wireframe♪ node_lock
Three steps: set the role, state the goal and limits, paste one good example, then let it run.
on-screen: Step: role, goal, one example
expected on screen: white ground · a BlueprintGrid panel over a dimmed Signal Field · Magister leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id BlueprintGridvisual pipelineshape knotground whitetreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Step: role, goal, one examplecurate rows, stages, steps
9s9
matches intent
shared field
signature-3d
resolve60.9–68.6scoalescenceicon·color♪ bed_out
Treat the model like a sharp new hire on day one, and it gives you a sharp new hire's work.
on-screen: Brief it like a smart new hire
expected on screen: white ground · knot hero in the shared Signal Field · Magister leads · coalescence · coalescence · icon·color logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape knotground whitetreatment colormotion coalescencepower coalescenceinstrument coalescence→Brief it like a smart new hire

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 9 destinations

LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBluesky

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

tiktokAI is a tool, not a wizard who knows your business. Here's the move: brief it like a new hire, tell it who to be, what you want, and the limits. Then show it ONE example of what good looks like, because a model copies a pattern better than a rule. Specific beats fancy.
instagramAI is a tool, not a wizard. Give it role, goal, and limits. Show it one good example. Specific beats fancy wording. #ai #artificialintelligence #prompting #aitools #productivity
linkedinThe plainest truth about this whole wave: the model is a tool, not a wizard who knows your business. The move: tell it who to be, what you want, and the limits, the same way you'd brief a new hire. A real brief returns real work; a vague wish returns a vague answer. Clever wording isn't the trick, being specific about the job is. Then show it one example of what good looks like, because a model copies a pattern far better than a rule, and the next answer matches that level. Treat the model like a sharp new hire on day one, and it gives you a sharp new hire's work.
xAI is a tool, not a wizard who knows your business. Brief it like a new hire: who to be, what you want, the limits. Then show it ONE example of good, because it copies a pattern better than a rule. Specific beats fancy. temerarii.com
facebookAI is a tool, not a wizard who knows your business. Brief it like a new hire: tell it who to be, what you want, and the limits. Then show it one example of what good looks like, because a model copies a pattern better than a rule. Specific beats fancy wording. temerarii.com
threadsAI is a tool, not a wizard who knows your business. Brief it like a new hire: who to be, what you want, the limits. Then show it ONE example of good, because it copies a pattern better than a rule. Specific beats fancy wording.
pinterestHow to actually use AI: brief it like a new hire with a role, a goal, and limits, then show it one example of good so it copies the pattern. Prompting basics, AI for beginners, getting better AI output, prompt engineering, practical AI tips.
blueskyAI is a tool, not a wizard who knows your business. Brief it like a new hire: who to be, what you want, the limits. Then show it ONE example of good, because it copies a pattern better than a rule. Specific beats fancy. temerarii.com
youtubeArtificial Intelligence: Brief It Like a New Hire The plainest truth about this whole wave is that the model is a tool, not a wizard who knows your business. This short shows the move: tell it who to be, what you want, and the limits, the same way you'd brief a new hire. A real brief returns real work; a vague wish returns a vague answer. Then show it one example of what good looks like, because a model copies a pattern far better than a rule. Clever wording isn't the trick. Being specific about the job is. #ai #artificialintelligence #prompting

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