Checklist the per-video bar — engine/sim
80.3/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-minus-the-hype-W25-Thu 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 · 26.2s · 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 | Slap a chatbot on the site and fire support, they said. Then it makes up answers and your customers stop trusting it. on-screen: "Chatbot = customer service" |
expected on screen: white ground · box hero in the shared Signal Field · Faber leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape boxground whitetreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→"Chatbot = customer service" | |||||||
| 2 |  matches intent CodeWindow template | diff | 5.0–11.0s | crossfade-8f | icon·wireframe | ♪ node_lock | The real method: retrieval over your actual help docs, so every answer cites a real page. on-screen: Ground it in your docs |
expected on screen: white ground · a CodeWindow panel over a dimmed Signal Field · Faber leads · code · crossfade-8f · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id CodeWindowvisual codeshape boxground whitetreatment wireframemotion crossfade-8fpower morphinstrument morph→Ground it in your docscurate codeLines, windowTitle | |||||||
| 3 |  matches intent NumberedList template | teach | 11.0–16.2s | kinetic-build | icon·wireframe | ♪ node_lock | The cost is keeping those docs current, the bot is only as honest as your knowledge base. on-screen: The cost: clean docs |
expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Faber leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape boxground whitetreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→The cost: clean docscurate items, nodes | |||||||
| 4 |  first render · fix pending StatScoreboard templatedead_airgeneric_scene | proof | 16.2–21.2s | receipts-count | icon·wireframe | ♪ node_lock | Minus the Hype |
expected on screen: white ground · a StatScoreboard panel over a dimmed Signal Field · Faber leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape boxground whitetreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Minus the Hypecurate pillar, stats, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 21.2–26.2s | coalescence | icon·color | ♪ bed_out | Minus the Hype |
expected on screen: white ground · box hero in the shared Signal Field · Faber leads · coalescence · coalescence · icon·color logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape boxground whitetreatment colormotion 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)
tiktokThey said slap a chatbot on the site and fire support. The real method: retrieval over your actual help docs, so every answer cites a real page. The cost is keeping those docs current. The bot is only as honest as your knowledge base. (AI-assisted)
instagram"Chatbot = customer service."
Not quite.
The real method: retrieval over your real help docs, so every answer cites a real page.
The bot is only as honest as your knowledge base.
#chatbot #rag #customersupport #aimarketing #thebigtm
linkedinThe pitch: slap a chatbot on the site and fire your support team. The reality: it confidently makes things up.
The method that works is retrieval over your actual help docs, so every answer cites a real page a human wrote. No page, no answer.
The cost is honest: you have to keep those docs current. The bot is only as good as the knowledge base behind it. That is a content job, not a hype one.
x"Chatbot = fire support."
Then it makes things up.
The method: retrieval over your real help docs, so every answer cites a real page. The bot is only as honest as your knowledge base.
temerarii.xyz/build
facebookThey said slap a chatbot on the site and fire support. Here is what actually works: retrieval over your real help docs, so every answer cites a real page. The catch is honest, you have to keep those docs current. The bot is only as good as the knowledge base behind it. One clear method, no hype.
threads"Chatbot = customer service, fire support." Then it confidently makes things up.
The real method: retrieval over your actual help docs, so every answer cites a real page.
The cost: keeping those docs current. The bot is only as honest as your knowledge base.
pinterestHow to build a support chatbot that does not lie: use retrieval over your real help docs so every answer cites a real page. The trade-off is keeping docs current, because the bot is only as honest as your knowledge base. A grounded RAG support method from The Big T-M.
bluesky"Chatbot = fire support." Then it makes things up. The method: retrieval over your real help docs, so every answer cites a real page. The bot is only as honest as your knowledge base.
youtubeTitle: Why Most Support Chatbots Lie (And the Fix) | Minus the Hype
The pitch says slap a chatbot on your site and fire support. In practice it makes things up. The method that works is retrieval over your actual help docs, so every answer cites a real page. The cost is keeping those docs current, because the bot is only as honest as your knowledge base. The Big T-M, method-only.