Checklist the per-video bar — engine/sim
77.8/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W28-Mon 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 · 27.5s · 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 | hook | 0–5.0s | kinetic-build | icon·wireframe | ♪ node_lock | Ask AI a question, get the answer, fire the analyst, they say. on-screen: "Replace your analyst" |
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape octaground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→"Replace your analyst" | |||||||
| 2 |  matches intent JsonDiff template | diff | 5.0–12.5s | crossfade-8f | icon·wireframe | ♪ node_lock | What works: hand the model your table schema and a few example queries, then it writes SQL you can read and check. on-screen: Give it the schema |
expected on screen: white ground · a JsonDiff panel over a dimmed Signal Field · Lumen leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape octaground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Give it the schemacurate codeLines, fileName, lines | |||||||
| 3 |  first render · fix pending ChecklistCard templatedead_air | teach | 12.5–17.5s | kinetic-build | icon·wireframe | ♪ node_lock | The cost is you still have to understand the query, because you read each line before you run it on real data. on-screen: The cost: verifying SQL |
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape octaground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→The cost: verifying SQLcurate items, nodes | |||||||
| 4 |  first render · fix pending ComparisonTable templatedead_airgeneric_scene | proof | 17.5–22.5s | receipts-count | icon·wireframe | ♪ node_lock | Minus the Hype |
expected on screen: white ground · a ComparisonTable panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id ComparisonTablevisual receiptsshape octaground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate colA, colB, rows, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 22.5–27.5s | coalescence | icon·ember-fill | ♪ bed_out | Minus the Hype |
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·ember-fill logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground whitetreatment ember-fillmotion coalescencepower coalescenceinstrument coalescence→Minus the Hype | |||||||
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)
tiktok"Ask AI, fire the analyst," they say. Real move: hand the model your table schema and a few example queries, then it writes SQL you can read. The cost? You still have to understand the query. (AI-assisted)
instagram"Replace your analyst."
Minus the hype:
Give the model your schema + a few example queries.
It writes SQL you can read and check.
The cost: you still have to understand the query.
#AItruth #SQL #dataops #minusthehype #plainlanguage
linkedinMinus the hype: "Ask AI a question, get the answer, fire the analyst."
Here is what actually works. Hand the model your table schema and a few example queries. It writes SQL you can read and check before you run it. That is a real, useful move.
The honest cost: you still have to understand the query. The model gets you a draft fast, but reading SQL is still the job. The analyst does not disappear; the blank-page part does.
Try it on one report this week and check the query yourself.
x"Ask AI, fire the analyst," they say. What works: give the model your schema and a few example queries, it writes SQL you can read. The cost: you still have to understand the query. temerarii.xyz
facebookYou have heard it: ask AI a question and fire the analyst. Here is the honest version. Hand the model your table schema and a few example queries, and it writes SQL you can read and check. The catch is you still have to understand the query. Try it on one report and read the SQL yourself.
threads"Replace your analyst," they say.
What works: hand the model your table schema and a few example queries. It writes SQL you can read and check.
The cost? You still have to understand the query. The blank page goes away. The thinking does not.
pinterestCan AI replace your data analyst? Minus the hype. The real method: give the model your table schema plus a few example queries, and it writes SQL you can read and verify. The honest cost is that you still have to understand the query before you run it. A plain-language take on AI for data work.
bluesky"Ask AI, fire the analyst," they say. What works: give the model your schema and example queries, it writes SQL you can read. The cost: you still have to understand the query.
youtubeTitle: Minus the Hype: No, AI Will Not Replace Your Analyst
The pitch is ask AI a question and fire the analyst. The real method: hand the model your table schema and a few example queries, and it writes SQL you can read and check. The honest cost is that you still have to understand the query before you run it. Try it on one report this week.