Checklist the per-video bar — engine/sim
82.8/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-build-log-W43-Wed good|bad)⚠ 6 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 6 scenes · 33.0s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent shared field signature-3d | open | 0–7.5s | spatial-parallax | icon·white-knockout | ♪ bed_in | Week twenty-one. We shipped automated lead enrichment this week, every new contact filled out before a human sees it. on-screen: Shipped: a lead enrichment step |
expected on screen: red ground · dodeca hero in the shared Signal Field · Mensor leads · node-graph · spatial-parallax · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape dodecaground redtreatment white-knockoutmotion spatial-parallaxpower summoninstrument summon→Shipped: a lead enrichment step | |||||||
| 2 |  matches intent LogStream template | build | 7.5–12.5s | type-on | icon·white-knockout | ♪ node_lock | The old way was opening five tabs to research each lead. You typed the same name into each tool by hand. on-screen: Old way: research each lead by hand |
expected on screen: red ground · a LogStream panel over a dimmed Signal Field · Mensor leads · code · type-on · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id LogStreamvisual codeshape dodecaground redtreatment white-knockoutmotion type-onpower summoninstrument draw-on→Old way: research each lead by handcurate codeLines, rows | |||||||
| 3 |  matches intent JsonDiff template | diff | 12.5–17.6s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | It broke on trust. The enrichment overwrote a correct field with a worse guess. on-screen: What broke: it overwrote good data |
expected on screen: red ground · a JsonDiff panel over a dimmed Signal Field · Mensor leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape dodecaground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→What broke: it overwrote good datacurate codeLines, fileName, lines | |||||||
| 4 |  matches intent SchematicCard template | step | 17.6–23.0s | kinetic-build | icon·white-knockout | ♪ node_lock | Now leads arrive already researched. Next, we add an automatic fit score. on-screen: Next: score the lead too |
expected on screen: red ground · a SchematicCard panel over a dimmed Signal Field · Mensor leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id SchematicCardvisual pipelineshape dodecaground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Next: score the lead toocurate nodes, stages, steps | |||||||
| 5 |  first render · fix pending StatScoreboard templatedead_airgeneric_scene | proof | 23.0–28.0s | receipts-count | icon·liquid-chrome | ♪ node_lock | Build Log |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape dodecaground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Build Logcurate pillar, stats, statsLabels | |||||||
| 6 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 28.0–33.0s | coalescence | icon·white-knockout | ♪ bed_out | Build Log |
expected on screen: red ground · dodeca hero in the shared Signal Field · Mensor leads · coalescence · coalescence · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape dodecaground redtreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→Build Log | |||||||
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)
tiktokBuild log: we shipped automated lead enrichment. Every new contact gets filled out before a human sees it. The old way meant five tabs per lead. It broke once by overwriting good data. Next we add an auto fit-score. (AI-assisted)
instagramBuild log: lead enrichment shipped.
New contacts arrive already researched.
No more five tabs per lead.
It broke once: overwrote a good field.
Next: an automatic fit score.
#buildinpublic #automation #leadgen #b2b #buildlog
linkedinBuild log, this week: we shipped automated lead enrichment. Every new contact is filled out before a human sees it.
The old way was opening five tabs to research each lead by hand. What broke: the enrichment once overwrote a correct field with a worse guess, so we added a trust check.
Now leads arrive already researched. Next, we add an automatic fit score so the team knows where to spend time. Shipping in public, including the parts that broke.
xBuild log: shipped automated lead enrichment. New contacts arrive researched, no more five tabs per lead. It broke once by overwriting good data. Next: an auto fit-score. temerarii.xyz
facebookThis week's build log: we shipped automated lead enrichment, so every new contact is filled out before a human sees it. The old way meant opening five tabs per lead. It broke once by overwriting a good field, which we fixed. Next up: an automatic fit score. Follow along at temerarii.xyz.
threadsBuild log this week: shipped automated lead enrichment.
Every new contact arrives filled out before a human sees it. The old way was five tabs per lead. What broke: it once overwrote a correct field with a worse guess. Next, we add an automatic fit score. Building in public, breaks included.
pinterestBuild in public log: automated lead enrichment for a CRM. Every new contact is researched and filled out before a human sees it, replacing manual five-tab research. Includes the failure mode (overwriting correct data) and the next step, an automatic lead fit score. Practical B2B automation.
blueskyBuild log: shipped automated lead enrichment. New contacts arrive researched, no more five tabs per lead. It broke once by overwriting good data. Next: an auto fit-score.
youtubeTitle: Build Log: Shipping Automated Lead Enrichment (and What Broke)
This week we shipped automated lead enrichment so every new contact is filled out before a human sees it, replacing manual five-tab research. We cover the failure mode, where it overwrote correct data with a worse guess, and what is next: an automatic fit score. More build logs at temerarii.xyz.