Checklist the per-video bar — engine/sim
86.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W33-Thu-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
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 · 65.7s · 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 | 0–7.7s | spatial-parallax | icon·liquid-chrome | ♪ bed_in | A marketer can now ask the data a plain question and get a real answer, no waiting on an analyst. on-screen: Marketers can now ask the data directly |
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→Marketers can now ask the data directly | |||||||
| 2 |  matches intent shared field signature-3d | hook | 7.7–14.7s | kinetic-build | icon·white-knockout | ♪ node_lock | Old way, you emailed the data team for one number and got it back, maybe, sometime next week. on-screen: The old way: beg for a report |
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→The old way: beg for a report | |||||||
| 3 |  matches intent NumberedList template | teach | 14.7–22.4s | kinetic-build | icon·liquid-chrome | ♪ node_lock | Here is the move: describe the question in plain words and let a model write the query against your data. on-screen: Ask the model to write the query |
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→Ask the model to write the querycurate items, nodes | |||||||
| 4 |  matches intent RankList template | proof | 22.4–29.7s | receipts-count | icon·white-knockout | ♪ node_lock | You ask which channel brought the buyers who stayed, and the model writes the pull and shows the table. on-screen: Plain question, real numbers back |
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→Plain question, real numbers backcurate rows, statsLabels | |||||||
| 5 |  matches intent StackTrace template | diff | 29.7–36.7s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | Waiting a week for one chart is over. Reading your own numbers in minutes is the new normal. on-screen: Read your data, don't beg |
expected on screen: red ground · a StackTrace panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StackTracevisual codeshape boxground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→Read your data, don't begcurate codeLines, errMsg, errType, fix, frames | |||||||
| 6 |  matches intent ChecklistCard template | teach | 36.7–44.0s | kinetic-build | icon·white-knockout | ♪ node_lock | Now the rule: read the query the model wrote, because a confident wrong answer is worse than no answer. on-screen: Check the query, not just answer |
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→Check the query, not just answercurate items, nodes | |||||||
| 7 |  matches intent StatScoreboard template | proof | 44.0–51.0s | receipts-count | icon·liquid-chrome | ♪ node_lock | Once you confirm the logic matches your question, you can trust the number and act on it today. on-screen: Verify the logic, trust the result |
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→Verify the logic, trust the resultcurate pillar, stats, statsLabels | |||||||
| 8 |  matches intent FlowSchematic template | step | 51.0–58.7s | kinetic-build | icon·white-knockout | ♪ node_lock | Three steps: ask in plain words, let the model write the query, then verify the logic before you believe it. on-screen: Step: ask, generate query, verify |
expected on screen: red ground · a FlowSchematic panel over a dimmed Signal Field · Faber leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id FlowSchematicvisual pipelineshape boxground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Step: ask, generate query, verifycurate stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 58.7–65.7s | coalescence | icon·liquid-chrome | ♪ bed_out | You no longer need the syntax. You need a sharp question and the patience to check the answer. on-screen: Curiosity, not SQL, is the skill |
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→Curiosity, not SQL, is the skill | |||||||
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)
tiktokMarketers can now ask their data a plain question and get a real answer. (AI-assisted) The move: describe the question in words, let a model write the query against your data. But ALWAYS read the query it wrote, a confident wrong answer is worse than none. Curiosity, not SQL, is the skill.
instagramAsk your data a plain question.
Describe it in words.
Let AI write the query.
Always check the query, not just the answer.
#dataanalytics #marketinganalytics #aitools #data #marketing
linkedinA marketer can now ask the data a plain question and get a real answer, no waiting on an analyst.
The move: describe the question in plain words, like which channel brought the buyers who stayed, and let a model write the query against your data, then show the table. But here's the rule: read the query the model wrote, because a confident wrong answer is worse than no answer. Once you confirm the logic matches your question, you can trust the number and act today.
You no longer need the syntax. You need a sharp question and the patience to check the answer.
xMarketers can now ask their data a plain question and get a real answer.
Describe it in words, let a model write the query, then ALWAYS read the query it wrote.
A confident wrong answer beats no answer? No. Curiosity is the skill.
temerarii.com
facebookMarketers can now ask their data a plain question and get a real answer. Describe the question in words and let a model write the query against your data. But always read the query it wrote, because a confident wrong answer is worse than no answer. You need a sharp question, not the syntax. temerarii.com
threadsMarketers can now ask their data a plain question and get a real answer.
Describe it in words, let a model write the query, then ALWAYS read the query it wrote. A confident wrong answer is worse than none.
Curiosity, not SQL, is the skill.
pinterestData analytics for marketers: ask your data in plain words, let AI write the query, then verify the logic before you trust the number. Marketing analytics, natural language to SQL, data-driven marketing, attribution analysis, self-serve reporting.
blueskyMarketers can now ask their data a plain question and get a real answer. Describe it in words, let a model write the query, then always read the query it wrote. Curiosity, not SQL, is the skill. temerarii.com
youtubeData & Analytics for Marketers: Ask, Generate, Verify
A marketer can now ask the data a plain question and get a real answer, no waiting on an analyst. This short shows the move: describe the question in plain words, like which channel brought the buyers who stayed, and let a model write the query against your data. But the rule matters: read the query the model wrote, because a confident wrong answer is worse than no answer. Confirm the logic, then trust the number.
You no longer need the syntax. You need a sharp question.
#dataanalytics #marketinganalytics #data