Checklist the per-video bar — engine/sim
84.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review thread-field-notes-W32-Sat good|bad)⚠ 5 flag(s) — not yet ship-ready: low_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 · 31.7s · 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 | 0–6.2s | kinetic-build | icon·color | ♪ node_lock | Field note. You keep exporting CSVs just so you can ask an AI a question about your own database. on-screen: Exporting CSVs to ask AI |
expected on screen: white ground · cone hero in the shared Signal Field · Augur leads · mark · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape coneground whitetreatment colormotion kinetic-buildpower laser-lockinstrument laser-trace→Exporting CSVs to ask AI | |||||||
| 2 |  matches intent ChecklistCard template | teach | 6.2–14.3s | kinetic-build | icon·color | ♪ node_lock | Old loop: export, upload, ask, repeat, with stale data. Now: connect an Airtable MCP server to the model. on-screen: Point the model at your base |
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape coneground whitetreatment colormotion kinetic-buildpower morphinstrument morph+laser→Point the model at your basecurate items, nodes | |||||||
| 3 |  matches intent DiffCard template | diff | 14.3–21.700000000000003s | crossfade-8f | icon·color | ♪ node_lock | Hook up one base over MCP and ask it a question you'd normally export for. Live answer, zero CSVs. on-screen: Connect one base this week |
expected on screen: white ground · a DiffCard panel over a dimmed Signal Field · Augur leads · code · crossfade-8f · icon·color logo · caption bottom-left spec (the prompt): comp_id DiffCardvisual codeshape coneground whitetreatment colormotion crossfade-8fpower morphinstrument morph→Connect one base this weekcurate codeLines, lines | |||||||
| 4 |  first render · fix pending PipelineMap templatedead_airgeneric_scene | proof | 21.7–26.7s | receipts-count | icon·color | ♪ node_lock | Field Notes |
expected on screen: white ground · a PipelineMap panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·color logo · caption bottom-left spec (the prompt): comp_id PipelineMapvisual receiptsshape coneground whitetreatment colormotion receipts-countpower receiptsinstrument spotlight→Field Notescurate stages, statsLabels | |||||||
| 5 |  first render · fix pending shared field signature-3ddead_airgeneric_scene | resolve | 26.7–31.7s | coalescence | icon·wireframe | ♪ bed_out | Field Notes |
expected on screen: white ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·wireframe logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground whitetreatment wireframemotion coalescencepower coalescenceinstrument coalescence→Field Notes | |||||||
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)
tiktokField note: you keep exporting CSVs just to ask an AI a question about your own database. The old loop is export, upload, ask, repeat, with stale data. Now connect an Airtable MCP server to the model and ask it live. Hook up one base this week, zero CSVs. (AI-assisted)
instagramStop exporting CSVs to ask AI about your own data.
Old loop:
export, upload, ask, repeat.
Always stale.
New loop:
connect an Airtable MCP server to the model.
Ask it live.
Hook up one base this week. Zero CSVs.
#airtable #mcp #aitools #nocode #buildinpublic
linkedinField note from this week. A lot of teams keep exporting CSVs just to ask an AI a question about their own database. The data is stale the moment it leaves the system.
The old loop is export, upload, ask, and repeat. The fix is to connect an Airtable MCP server directly to the model, so it can read the live base and answer questions against current data.
The starting move is small: hook up one base over MCP this week and ask it a question you would normally export for. You get a live answer and zero CSVs. Once one base is wired, the rest follow the same pattern.
xField note: you keep exporting CSVs just to ask AI about your own database. The fix: connect an Airtable MCP server to the model and ask it live. Hook up one base this week, zero CSVs. temerarii.xyz
facebookField note from this week: a lot of us keep exporting CSVs just to ask an AI a question about our own database, and the data is stale the moment it leaves. The fix is to connect an Airtable MCP server to the model so it reads the live base. Hook up one base this week and ask it a question you would normally export for. Live answer, zero CSVs. More at temerarii.xyz.
threadsField note: you keep exporting CSVs just to ask AI a question about your own database. Old loop: export, upload, ask, repeat, always stale. Now connect an Airtable MCP server to the model and ask it live. Hook up one base this week and skip the CSVs.
pinterestField note on connecting AI to your live database. Why exporting CSVs to ask AI gives you stale data, how an Airtable MCP server lets a model read your base directly, and a one-base starting step to get live answers with no exports.
blueskyField note: you keep exporting CSVs just to ask AI about your own database. The fix: connect an Airtable MCP server to the model and ask it live. Hook up one base this week, zero CSVs.
youtubeTitle: Stop Exporting CSVs to Ask AI About Your Own Data (Use MCP)
Field note from this week. A lot of teams keep exporting CSVs just to ask an AI a question about their own database, and the data is stale the moment it leaves. The fix is to connect an Airtable MCP server directly to the model so it reads the live base. The starting move: hook up one base over MCP, ask a question you would normally export for, and get a live answer with zero CSVs. More at temerarii.xyz.