Checklist the per-video bar — engine/sim
86.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W31-Sun-1 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
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 · 58.9s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent shared field signature-3d | open | 0–5.9s | spatial-parallax | icon·liquid-chrome | ♪ bed_in | Once, shipping software meant a stack of tickets and a prayer to the build gods. on-screen: Shipping software, the old way |
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape boxground redtreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→Shipping software, the old way | |||||||
| 2 |  matches intent shared field signature-3d | hook | 5.9–11.8s | kinetic-build | icon·white-knockout | ♪ node_lock | Here is the dark truth: most code you write is plumbing nobody will ever read. on-screen: Most code is plumbing |
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape boxground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→Most code is plumbing | |||||||
| 3 |  matches intent NumberedList template | teach | 11.8–19.1s | kinetic-build | icon·liquid-chrome | ♪ node_lock | So we do it now with a model in the loop. Write the failing test first, in plain words. on-screen: Write the test first |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape boxground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Write the test firstcurate items, nodes | |||||||
| 4 |  matches intent RankList template | proof | 19.1–26.1s | receipts-count | icon·white-knockout | ♪ node_lock | Then let the model write code until the test passes. The test is the spec, not a wish. on-screen: Test drives the code |
expected on screen: red ground · a RankList panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape boxground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Test drives the codecurate rows, statsLabels | |||||||
| 5 |  matches intent LogStream template | diff | 26.1–32.7s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | Old way you hoped it worked. New way the green check is your receipt before you merge. on-screen: Old: hope. New: proof |
expected on screen: red ground · a LogStream panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id LogStreamvisual codeshape boxground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→Old: hope. New: proofcurate codeLines, rows | |||||||
| 6 |  matches intent ChecklistCard template | teach | 32.7–39.0s | kinetic-build | icon·white-knockout | ♪ node_lock | Pin every package version exactly, so the build today builds the same a year from now. on-screen: Pin every version |
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape boxground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Pin every versioncurate items, nodes | |||||||
| 7 |  matches intent StatScoreboard template | proof | 39.0–45.6s | receipts-count | icon·liquid-chrome | ♪ node_lock | We do this at The Big T-M. A locked file means the machine never surprises you twice. on-screen: Same build, every time |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape boxground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Same build, every timecurate pillar, stats, statsLabels | |||||||
| 8 |  matches intent ListCard template | step | 45.6–51.9s | kinetic-build | icon·white-knockout | ♪ node_lock | Your move: write the test, let the model fill it, pin the versions, ship the receipt. on-screen: Steps: test, model, pin |
expected on screen: red ground · a ListCard panel over a dimmed Signal Field · Faber leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ListCardvisual pipelineshape boxground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Steps: test, model, pincurate items, stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 51.9–58.9s | coalescence | icon·liquid-chrome | ♪ bed_out | Now anyone on the team can change the code and the test tells the truth, not the ego. on-screen: Code you can trust |
expected on screen: red ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Code you can trust | |||||||
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)
tiktokHow we ship software now: write the failing test FIRST, then let AI fill the code until it goes green. The test is the spec. (AI-assisted) Pin your versions so today's build = next year's build. #softwaredevelopment #codingtips
instagramTest first. Code second.
The green check is your receipt.
Pin every version so the build never lies.
#softwaredevelopment #testdriven #devtips #buildinpublic #temerarii
linkedinThe most useful change we made to shipping software: write the failing test in plain language first, then let a model write code until it passes. The test becomes the spec, not a hope. Then pin every dependency version exactly so the build is reproducible a year out. Receipts over vibes.
xWrite the failing test first. Let the model fill the code till it's green. Pin every version. The build stops surprising you. temerarii.com
facebookWe changed how we ship software: write the failing test first, let AI write code until it passes, then pin every version so the build is the same a year from now. Want the full method? It's free on the site.
threadsMost code is plumbing nobody reads. So write the failing test first, let the model fill it in, and pin your versions. The green check is your receipt, not your ego.
pinterestTest-driven development with AI: how to write the failing test first, let a model write the code until it passes, and pin dependency versions for reproducible builds. Software development tips and a repeatable shipping workflow.
blueskyWrite the failing test first. Let the model fill the code until it's green. Pin every version. The build stops lying to you. temerarii.com
youtubeShip Software With AI: Test-First, Then Pin Every Version
The real method: write the failing test in plain language, let a model write code until it passes, then pin every dependency exactly so today's build equals next year's build. The test is the spec; the green check is your receipt. AI-assisted, fully reproducible. More free at temerarii.com