Checklist the per-video bar — engine/sim
86.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W30-Tue-2 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 · 59.0s · 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 | 0–5.9s | spatial-parallax | icon·wireframe | ♪ bed_in | Marketers used to drown in data, a thousand rows and no idea which one mattered. on-screen: Marketing data drowned the marketer |
expected on screen: white ground · knot hero in the shared Signal Field · Magister leads · node-graph · spatial-parallax · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape knotground whitetreatment wireframemotion spatial-parallaxpower summoninstrument summon→Marketing data drowned the marketer | |||||||
| 2 |  matches intent shared field signature-3d | hook | 5.9–12.2s | kinetic-build | icon·wireframe | ♪ node_lock | Now you can ask the table a plain question and get the answer back in seconds. on-screen: Now you ask the table a question |
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→Now you ask the table a question | |||||||
| 3 |  matches intent NumberedList template | teach | 12.2–18.5s | kinetic-build | icon·wireframe | ♪ node_lock | Drop your CSV into a model and ask which campaign drove the most signups last month. on-screen: Hand the model your CSV and ask |
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→Hand the model your CSV and askcurate items, nodes | |||||||
| 4 |  matches intent RankList template | proof | 18.5–25.1s | receipts-count | icon·wireframe | ♪ node_lock | It writes the query, runs it in your head's place, and hands back the answer in words. on-screen: It writes the query, you read the |
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→It writes the query, you read the answercurate rows, statsLabels | |||||||
| 5 |  matches intent CodeWindow template | diff | 25.1–32.1s | crossfade-8f | icon·wireframe | ♪ node_lock | A model can be confidently wrong. We always check its math against the raw numbers before we act. on-screen: We check the math, we don't trust |
expected on screen: white ground · a CodeWindow panel over a dimmed Signal Field · Magister leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id CodeWindowvisual codeshape knotground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→We check the math, we don't trust it blindcurate codeLines, windowTitle | |||||||
| 6 |  matches intent ChecklistCard template | teach | 32.1–39.1s | kinetic-build | icon·wireframe | ♪ node_lock | Ask it to show the exact rows behind every claim, so the answer is auditable, not a vibe. on-screen: Make it show the rows behind the |
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→Make it show the rows behind the claimcurate items, nodes | |||||||
| 7 |  matches intent StatScoreboard template | proof | 39.1–45.4s | receipts-count | icon·wireframe | ♪ node_lock | Analysis that took an analyst two days now takes you ten minutes and a follow-up question. on-screen: Analysis goes from days to minutes |
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→Analysis goes from days to minutescurate pillar, stats, statsLabels | |||||||
| 8 |  matches intent StepFlow template | step | 45.4–52.0s | kinetic-build | icon·wireframe | ♪ node_lock | Your move: take last month's CSV, ask one real question, and demand the rows behind the answer. on-screen: Your move |
expected on screen: white ground · a StepFlow panel over a dimmed Signal Field · Magister leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id StepFlowvisual pipelineshape knotground whitetreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Your move: ask one question of your datacurate stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 52.0–59.0s | coalescence | icon·wireframe | ♪ bed_out | The edge is not the data, it is the question. Be the marketer who asks the sharp one. on-screen: Be the one who asks better questions |
expected on screen: white ground · knot hero in the shared Signal Field · Magister leads · coalescence · coalescence · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape knotground whitetreatment wireframemotion coalescencepower coalescenceinstrument coalescence→Be the one who asks better questions | |||||||
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)
tiktokDrowning in marketing data? Drop your CSV into a model, ask 'which campaign drove the most signups?', then make it SHOW the rows behind the answer. Check the math. The edge is the question. (AI-assisted.)
instagramThe edge isn't the data.
It's the question.
Ask → demand the rows → check the math.
#dataanalytics #marketingdata #aiformarketers #datadriven #temerarii
linkedinMarketers used to drown in data: a thousand rows and no idea which one mattered. Now you can ask the table a plain question. Drop your CSV into a model, ask which campaign drove the most signups last month, and have it write and run the query. The discipline: a model can be confidently wrong, so always make it show the exact rows behind every claim and check the math against the raw numbers. Takeaway: the edge is the question, not the data.
xDrowning in marketing data? Drop your CSV into a model, ask which campaign drove the most signups, then make it show the rows behind the answer. Check the math. temerarii.xyz
facebookMarketers used to drown in data with no idea which row mattered. Now you ask the table a plain question: drop your CSV into a model and ask which campaign drove the most signups last month. Just make it show the exact rows behind every claim and check the math, because a model can be confidently wrong. The edge is the question. Full method on the site.
threadsData for marketers: drop your CSV into a model, ask a plain question like 'which campaign drove the most signups?', then make it show the rows behind the answer and check the math. The edge is the question.
pinterestHow marketers can analyze data with AI: drop your CSV into a model, ask a plain-language question like which campaign drove the most signups, and make it show the exact rows behind the answer. Always verify the math. Marketing analytics, data analysis for marketers, AI workflow.
blueskyData for marketers: drop your CSV into a model, ask a plain question, make it show the rows behind the answer, check the math. The edge is the question. temerarii.xyz
youtubeAsk Your Marketing Data a Question (AI Analysis, Verified)
Marketers used to drown in data with no idea which row mattered. Now you can ask the table a plain question. We show how: drop your CSV into a model, ask which campaign drove the most signups last month, and have it write and run the query. The discipline that keeps you honest: make it show the exact rows behind every claim and check the math against the raw numbers, because a model can be confidently wrong. The edge is the question.
Made with The Big T-M. AI-assisted.
more at temerarii.xyz