Checklist the per-video bar — engine/sim
98.5/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W27-Sun-1 good|bad)⚠ 1 flag(s) — not yet ship-ready: copy_generic · 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 · 63.0s · 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 | 0–5.5s | spatial-parallax | icon·liquid-chrome | ♪ bed_in | Most marketers still treat a dashboard like a dentist visit. Necessary, dreaded, over fast. on-screen: Most marketers fear the data |
expected on screen: black ground · knot hero in the shared Signal Field · Magister leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape knotground blacktreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→Most marketers fear the data | |||||||
| 2 |  matches intent shared field signature-3d | hook | 5.5–12.8s | kinetic-build | icon·wireframe | ♪ node_lock | Here is the part nobody tells you. You do not need a stats degree to read your own numbers. on-screen: You don't need a data degree |
expected on screen: black 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 blacktreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→You don't need a data degree | |||||||
| 3 |  matches intent NumberedList template | teach | 12.8–20.1s | kinetic-build | icon·wireframe | ♪ node_lock | Turn on the free GA4 to BigQuery export, and every click lands in a table you can actually query. on-screen: Pipe GA4 events to BigQuery |
expected on screen: black 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 blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Pipe GA4 events to BigQuerycurate items, nodes | |||||||
| 4 |  matches intent RankList template | proof | 20.1–27.400000000000002s | receipts-count | icon·wireframe | ♪ node_lock | Then ask a model to write the SQL for you. You type a question, it hands back the query. on-screen: Ask the table in plain words |
expected on screen: black 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 blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Ask the table in plain wordscurate rows, statsLabels | |||||||
| 5 |  matches intent BuildLog template | diff | 27.4–34.699999999999996s | crossfade-8f | icon·wireframe | ♪ node_lock | A normal report tells you what happened. Wire a model on top and it tells you what comes next. on-screen: Reports describe, this predicts |
expected on screen: black ground · a BuildLog panel over a dimmed Signal Field · Magister leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id BuildLogvisual codeshape knotground blacktreatment wireframemotion crossfade-8fpower morphinstrument morph→Reports describe, this predictscurate codeLines, lines | |||||||
| 6 |  matches intent ChecklistCard template | teach | 34.7–41.7s | kinetic-build | icon·wireframe | ♪ node_lock | Feed last quarter of deals into a small model and let it score tonight's leads while you sleep. on-screen: Score every lead nightly |
expected on screen: black 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 blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Score every lead nightlycurate items, nodes | |||||||
| 7 |  matches intent StatScoreboard template | proof | 41.7–48.0s | receipts-count | icon·wireframe | ♪ node_lock | Now your team calls the twelve leads it flagged, not the two hundred in the spreadsheet. on-screen: Chase the 12 it flags |
expected on screen: black 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 blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Chase the 12 it flagscurate pillar, stats, statsLabels | |||||||
| 8 |  matches intent WireframeMock template | step | 48.0–55.3s | kinetic-build | icon·wireframe | ♪ node_lock | So the move is simple. Export to BigQuery, ask in plain words, score leads, act on the short list. on-screen: Step: export, query, score, act |
expected on screen: black ground · a WireframeMock panel over a dimmed Signal Field · Magister leads · pipeline · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id WireframeMockvisual pipelineshape knotground blacktreatment wireframemotion kinetic-buildpower throwinstrument laser-trace→Step: export, query, score, actcurate stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 55.3–63.0s | coalescence | icon·liquid-chrome | ♪ bed_out | That is data that works the night shift. The Big T-M builds the pipe so you just read the answer. on-screen: Data that works the night shift |
expected on screen: black ground · knot hero in the shared Signal Field · Magister leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape knotground blacktreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Data that works the night shift | |||||||
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 marketers read their own data without a stats degree (AI-assisted). Turn on the free GA4 to BigQuery export, ask a model to write the SQL, then let it score tonight's leads overnight. You wake up to a short list, not a 200-row spreadsheet. Reports tell you what happened. A model tells you what's next.
instagramStop dreading the dashboard.
GA4 to BigQuery, free export.
Ask a model for the SQL.
Score leads overnight.
Wake up to a short list.
#marketinganalytics #ga4 #bigquery #aimarketing #datadriven
linkedinMost marketing teams treat analytics like a dental visit: necessary, dreaded, over fast.
The practical move for W27:
1. Turn on the free GA4 to BigQuery export so every event lands in a queryable table.
2. Use a model to translate plain-English questions into SQL. You stop waiting on an analyst.
3. Feed a quarter of closed deals into a small scoring model and let it rank tonight's leads overnight.
The difference: a report describes the past. A scoring layer points at the twelve leads worth calling tomorrow instead of the two hundred sitting in a sheet.
This is AI-assisted, and we disclose it. The takeaway is ownership: your team should be able to ask its own data a question and get an answer the same day.
xTurn on the free GA4 to BigQuery export. Ask a model to write the SQL. Let it score tonight's leads overnight. You wake up to 12 calls worth making, not 200. temerarii.com
facebookMost marketers treat the dashboard like a dental visit. Here's a calmer way: turn on the free GA4 to BigQuery export, ask a model to write the SQL for your questions, then let a small model score tonight's leads overnight. You wake up to a short call list instead of a giant spreadsheet. Want the setup? Visit temerarii.com.
threadsYou don't need a stats degree to read your own numbers. Turn on the free GA4 to BigQuery export, have a model write the SQL, and let it score tonight's leads overnight. Wake up to 12 calls worth making, not 200.
pinterestMarketing analytics for non-analysts: GA4 to BigQuery free export, AI-written SQL, and overnight lead scoring. A simple, evergreen workflow to turn raw event data into a short, prioritized call list every morning. Predictive marketing data made plain.
blueskyTurn on the free GA4 to BigQuery export, have a model write the SQL, and let it score tonight's leads overnight. Wake up to the 12 calls worth making, not 200. temerarii.com
youtubeMarketing Analytics Without a Stats Degree: GA4, BigQuery & AI Lead Scoring
Most marketers dread the dashboard. This walks through a calmer, more useful path: turn on the free GA4 to BigQuery export so every event becomes queryable, use a model to translate plain-English questions into SQL, and feed a quarter of closed deals into a small scoring model that ranks tonight's leads overnight. A report tells you what happened. A scoring layer tells you which twelve leads to call tomorrow. AI-assisted and disclosed. Learn more at temerarii.com.