Checklist the per-video bar — engine/sim
100.0/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review W31-case-studies-beat-2 good|bad)✓ all static checks pass — one-focal/scene · tier-by-beat · one-track caption · colorway · cast+shape correct · no banned/fabricated. (audio + visual tiers verify on the rendered finals — Phase 2)
Composition comp · template family · expected output
9:16 Reelrendered1:1 Squarerendered16:9 Widerendered9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
expected output: 3/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 6 scenes · 43.9s · 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 | 0–7.3s | spatial-parallax | icon·white-knockout | ♪ bed in | Most teams spend their best hours on tasks a machine should be handling, and the revenue work waits. on-screen: The work that eats your week |
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→The work that eats your week | |||||||
| 2 |  matches intent StatScoreboard template | stat | 7.3–14.8s | receipts-count | icon·white-knockout | ♪ — | We timed the busywork on one client. It was about eleven hours a week on reports, formatting, and copy. on-screen: 11 hours a week, gone |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape dodecaground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→html-in-canvas-receiptscurate pillar, stats, statsLabels | |||||||
| 3 |  matches intent ComparisonTable template | proof | 14.8–24.1s | receipts-count | icon·liquid-chrome | ♪ — | We moved the reports into a daily Python job that pulls GA4. Then Claude drafts the first copy from a brief. on-screen: We automated the boring parts |
expected on screen: red ground · a ComparisonTable panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id ComparisonTablevisual receiptsshape dodecaground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→We automated the boring partscurate colA, colB, rows, statsLabels | |||||||
| 4 |  matches intent RankList template | receipt | 24.1–31.400000000000002s | receipts-count | icon·white-knockout | ♪ — | Those eleven hours dropped to ninety minutes of review. We put the saved time back on the campaigns. on-screen: 11 hrs to 90 minutes |
expected on screen: red ground · a RankList panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape dodecaground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→11 hrs to 90 minutescurate rows, statsLabels | |||||||
| 5 |  matches intent KpiGrid template | stat | 31.4–37.9s | receipts-count | icon·liquid-chrome | ♪ — | Nothing that drives money got cut. We only dropped the parts a person did not need to do. on-screen: Revenue work, untouched |
expected on screen: red ground · a KpiGrid panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id KpiGridvisual receiptsshape dodecaground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Revenue work, untouchedcurate kpis, statsLabels | |||||||
| 6 |  matches intent shared field signature-3d | resolve | 37.9–43.9s | coalescence | icon·white-knockout | ♪ bed out | If you want your week back without losing the work that pays, the full breakdown is waiting for you on-screen: See the receipts · temerarii.xyz |
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→See the receipts · temerarii.xyz | |||||||
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 12 destinations
LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBlueskyEmailSMSBlog
Social captions supplemental published copy · per channel (comp_id level)
tiktokWe timed the busywork on one client account. Eleven hours a week on reports, formatting, and copy reps. We moved the reports to a daily Python job that pulls GA4, and let Claude draft the first copy. Eleven hours became ninety minutes of review. (AI-assisted)
instagramEleven hours a week, gone to busywork.
The fix:
Reports moved to a daily Python job pulling GA4.
First-pass copy drafted by Claude from a brief.
Review time: about ninety minutes.
Revenue work: untouched.
#marketingops #automation #ga4 #python #smallbusiness
linkedinWe clocked the busywork on one client account: about eleven hours a week on reporting, formatting, and copy reps. So we moved the reporting into a daily Python job that pulls the GA4 API, and let Claude draft the first-pass copy from a brief. Review now takes about ninety minutes. Nothing that drives revenue got cut. We only removed the parts a person did not need to do, and the saved time went back onto campaigns. The full breakdown, with the steps, is on temerarii.xyz.
xEleven hours a week on one account, gone to reports and copy reps. We moved it to a daily Python job pulling GA4, with Claude drafting first-pass copy. Down to 90 minutes of review. temerarii.xyz
facebookOne client account was eating about eleven hours a week on reporting, formatting, and copy reps. We moved the reports into a daily Python job that pulls GA4, and let Claude draft the first copy from a brief. Now it takes about ninety minutes to review, and the saved time goes back onto the work that pays. See the full breakdown at temerarii.xyz.
threadsEleven hours a week on one account, gone to reports and copy reps. We moved the reports to a daily Python job pulling GA4, and let Claude draft the first copy from a brief. Down to about ninety minutes of review. The revenue work never got touched. We only cut the parts a person did not need to do.
pinterestMarketing automation case study: how to cut eleven hours a week of reporting busywork. Move recurring reports into a scheduled Python job that pulls the GA4 API, then let an AI model draft first-pass copy from a brief. Review time drops to about ninety minutes, and revenue work stays untouched. A repeatable workflow for small marketing teams.
blueskyEleven hours a week on one account went to reports and copy reps. We moved reports to a daily Python job pulling GA4, with Claude drafting first-pass copy. Down to about 90 minutes of review.
youtubeTitle: 11 Hours a Week, Gone: How We Automated Client Reporting With Python + GA4
We timed the busywork on one client account at about eleven hours a week on reporting, formatting, and copy reps. In this breakdown we show how we moved reporting into a daily Python job that pulls the GA4 API, and let Claude draft first-pass copy from a brief. Review time dropped to about ninety minutes, and the revenue work stayed untouched. We share the method so you can rebuild it yourself.