Checklist the per-video bar — engine/sim
74.0/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-receipts-W41-Fri good|bad)⚠ 7 flag(s) — not yet ship-ready: copy_genericlow_vo_coveragedead_airgeneric_scene · see docs/strategy/VIDEO-CHECKLIST.md
Composition comp · template family · expected output
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 5 scenes · 25.0s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent KpiGrid template | stat | 0–5.0s | receipts-count | icon·liquid-chrome | ♪ node_lock | Thirty distinct scripts drafted in parallel by a swarm of agents in one run. on-screen: 30 scripts. 1 swarm. |
expected on screen: red ground · a KpiGrid panel over a dimmed Signal Field · Nexus leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id KpiGridvisual receiptsshape tetraground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→30 scripts. 1 swarm.curate kpis, statsLabels | |||||||
| 2 |  first render · fix pending RankList templatedead_air | proof | 5.0–10.0s | receipts-count | icon·white-knockout | ♪ node_lock | Writing each script one after another used to take days, since you start the next only when the last is done. on-screen: Agents in parallel. |
expected on screen: red ground · a RankList panel over a dimmed Signal Field · Nexus leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape tetraground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Agents in parallel.curate rows, statsLabels | |||||||
| 3 |  matches intent CodeWindow template | diff | 10.0–15.0s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | Give each agent the same brief and its own slot, then run them all at once. The writers' room of the future runs in parallel. on-screen: Fan out the writing. |
expected on screen: red ground · a CodeWindow panel over a dimmed Signal Field · Nexus leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id CodeWindowvisual codeshape tetraground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→Fan out the writing.curate codeLines, windowTitle | |||||||
| 4 |  first render · fix pending StepFlow templatedead_airgeneric_scene | step | 15.0–20.0s | kinetic-build | icon·white-knockout | ♪ node_lock | Receipts |
expected on screen: red ground · a StepFlow panel over a dimmed Signal Field · Nexus leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id StepFlowvisual pipelineshape tetraground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Receiptscurate stages, steps | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 20.0–25.0s | coalescence | icon·white-knockout | ♪ bed_out | Receipts |
expected on screen: red ground · tetra hero in the shared Signal Field · Nexus leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape tetraground redtreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→Receipts | |||||||
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)
tiktokReceipts: thirty distinct scripts, one swarm, one run. Writing them in sequence used to take days. The writers' room of the future runs in parallel. (AI-assisted)
instagram30 scripts. 1 swarm. 1 run.
Writing them in sequence took days.
Agents wrote them in parallel.
The writers' room runs side by side now.
#buildinpublic #aiagents #scriptwriting #receipts #temerarii
linkedinReceipts: thirty distinct scripts drafted in parallel by a swarm of agents in one run.
Writing each script in sequence used to take days, one after another. Splitting the work across agents that run side by side turned that into a single pass.
The method is simple to copy: give each agent the same brief and a distinct slot, then run them at once instead of in a line. The writers' room of the future runs in parallel.
xReceipts: 30 distinct scripts, one swarm, one run. Sequential writing took days. Run agents in parallel instead. temerarii.xyz
facebookHere is a receipt from our own work: thirty distinct scripts drafted in parallel by a swarm of agents in one run. Writing each one in sequence used to take days. The trick is to give each agent the same brief and run them side by side instead of one at a time. See how at temerarii.xyz.
threadsReceipts: thirty distinct scripts, one swarm, one run.
Writing them in sequence took days. Give each agent the same brief and a distinct slot, then run them all at once. The writers' room of the future runs in parallel.
pinterestHow to draft thirty scripts in one run: instead of writing each one in sequence over days, give a swarm of AI agents the same brief and distinct slots, then run them in parallel. A simple pattern for fanning out repetitive writing work.
blueskyReceipts: 30 distinct scripts, one swarm, one run. Sequential writing took days. Run the agents in parallel instead.
youtubeTitle: 30 Scripts, 1 Swarm: Fanning Out the Writers' Room
Receipts from our own pipeline: thirty distinct scripts drafted in parallel by a swarm of agents in a single run. Writing each script in sequence used to take days. The method: give each agent the same brief and a distinct slot, then run them side by side instead of one at a time. The writers' room of the future runs in parallel.