Checklist the per-video bar — engine/sim
82.4/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W49-Mon good|bad)⚠ 6 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 · 29.1s · 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 | 0–5.1s | kinetic-build | icon·wireframe | ♪ node_lock | The intel pitch: ask AI about your competitors and get a perfect market map. on-screen: "AI does your competitive research" |
expected on screen: white ground · tetra hero in the shared Signal Field · Nexus leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape tetraground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→"AI does your competitive research" | |||||||
| 2 |  matches intent JsonDiff template | diff | 5.1–12.8s | crossfade-8f | icon·wireframe | ♪ node_lock | Our real method: a scraper pulls rivals' live pages and prices, then the model sums up only what it just read. on-screen: Reality: scrape live, then sum up |
expected on screen: white ground · a JsonDiff panel over a dimmed Signal Field · Nexus leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape tetraground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Reality: scrape live, then sum upcurate codeLines, fileName, lines | |||||||
| 3 |  matches intent ChecklistCard template | teach | 12.8–19.1s | kinetic-build | icon·wireframe | ♪ node_lock | The real cost of trusting model memory is a strategy built on a competitor fact that was never true. on-screen: The cost: strategy on a hallucination |
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Nexus leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape tetraground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→The cost: strategy on a hallucinationcurate items, nodes | |||||||
| 4 |  first render · fix pending RankList templatedead_airgeneric_scene | proof | 19.1–24.1s | receipts-count | icon·wireframe | ♪ node_lock | Minus the Hype |
expected on screen: white ground · a RankList panel over a dimmed Signal Field · Nexus leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape tetraground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate rows, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 24.1–29.1s | coalescence | icon·3d-extrude | ♪ bed_out | Minus the Hype |
expected on screen: white ground · tetra hero in the shared Signal Field · Nexus leads · coalescence · coalescence · icon·3d-extrude logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape tetraground whitetreatment 3d-extrudemotion 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)
tiktokThe pitch: ask AI about your rivals and get a perfect market map.
Real method: a scraper pulls their live pages and prices, then the model sums up only what it just read.
Trust model memory and you build strategy on a fact that was never true. (AI-assisted)
instagram"AI does your competitive research."
Reality: scrape live, then summarize.
A scraper pulls rivals' real pages and prices. The model sums up only what it just read.
Trust its memory and you bet on a fake fact.
#competitiveresearch #ai #firecrawl #strategy #buildinpublic
linkedinThe pitch: ask AI about your competitors and get a perfect market map.
Our real method: a scraper pulls competitors' live pages and pricing through Firecrawl, and the model summarizes only what it just read.
The cost of skipping that step is real. Trust the model's memory and you build a strategy on a competitor fact that was never true.
Ground the model in fresh data. Then let it summarize.
x"AI does your competitive research." Reality: a scraper pulls rivals' live pages and prices, then the model sums up only what it just read. Trust its memory and you bet on a fact that was never true. temerarii.xyz
facebookThe pitch says AI can map your whole market for you. The real method is simpler: a scraper pulls your competitors' live pages and pricing, then the model summarizes only what it just read. Trust the model's memory instead and you can build a strategy on a fact that was never true. Ground it in fresh data first.
threads"AI does your competitive research."
Reality: scrape live, then summarize.
A scraper pulls rivals' real pages and prices. The model sums up only what it just read. Trust its memory instead and your strategy rests on a fact that was never true.
pinterestHow to do AI competitive research the right way: scrape competitors' live pages and pricing with a tool like Firecrawl, then have the model summarize only the fresh data it just read. Skip the scrape and trust model memory, and you risk building strategy on a competitor fact that was never true.
bluesky"AI does your competitive research." Reality: scrape rivals' live pages and prices first, then have the model sum up only what it just read. Trust its memory and you bet on a fact that was never true.
youtubeTitle: AI Competitive Research, Minus the Hype: Scrape Live, Then Summarize
The pitch says you can ask AI about your competitors and get a perfect market map. The real method: a scraper pulls competitors' live pages and pricing through Firecrawl, and the model summarizes only what it just read. The cost of trusting model memory instead is a strategy built on a competitor fact that was never true. More at temerarii.xyz.