Back Office · office.temerarii.xyz
One asset, all the way in — composition, the wireframe + storyboard, the output format stack, and the template, all read from the SAME content-index record. The expected output matches what /media surfaces for this post.
post thread-the-stack-W31-Tuekind threadweek W31date 2026-08-04campaign thread · Tuepillar performancebeat Tueasset videoduration 35.7sground blackscenes 6

Checklist the per-video bar — engine/sim

83.6/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review thread-the-stack-W31-Tue 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

composition SceneReelfamily / template SchematicCard
9:16 Reelrendered1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
▶ open rendered mp4
expected output: 1/7 rendered — same matrix the /media preview surfaces for this asset.

Composition layer × scene 6 scenes · 35.7s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d		hook0–5.0skinetic-buildicon·wireframe♪ node_lock
The tool is Notion, a lovely place to lose things, because its search only matches exact words.
on-screen: Notion search is weak
expected on screen: black ground · dodeca hero in the shared Signal Field · Mensor leads · mark · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual markshape dodecaground blacktreatment wireframemotion kinetic-buildpower laser-lockinstrument laser-trace→Notion search is weak
2s2
matches intent
NumberedList
template		teach5.0–13.4skinetic-buildicon·wireframe♪ node_lock
So we export the pages, embed them into vectors, and run semantic search. Now you find ideas by meaning, not exact words.
on-screen: Export + embed + vector search
expected on screen: black ground · a NumberedList panel over a dimmed Signal Field · Mensor leads · node-graph · kinetic-build · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id NumberedListvisual node-graphshape dodecaground blacktreatment wireframemotion kinetic-buildpower morphinstrument morph+laser→Export + embed + vector searchcurate items, nodes
3s3
matches intent
StackTrace
template		build13.4–20.7stype-onicon·wireframe♪ node_lock
Now your knowledge base answers questions in plain language, citing the exact page. It's a search engine for your own head.
on-screen: Ask your notes a question
expected on screen: black ground · a StackTrace panel over a dimmed Signal Field · Mensor leads · code · type-on · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id StackTracevisual codeshape dodecaground blacktreatment wireframemotion type-onpower summoninstrument draw-on→Ask your notes a questioncurate codeLines, errMsg, errType, fix, frames
4s4
matches intent
ListCard
template		proof20.7–25.7sreceipts-counticon·wireframe♪ node_lock
So export one Notion database, embed it, and ask it something fuzzy.
on-screen: Embed one workspace
expected on screen: black ground · a ListCard panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id ListCardvisual receiptsshape dodecaground blacktreatment wireframemotion receipts-countpower receiptsinstrument spotlight→Embed one workspacecurate items, statsLabels
5s5
first render · fix pending
shared field
signature-3ddead_airgeneric_scene		futurist25.7–30.7sspatial-parallaxicon·wireframe♪ bed
The Stack
expected on screen: black ground · dodeca hero in the shared Signal Field · Mensor leads · spatial-parallax · icon·wireframe logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldshape dodecaground blacktreatment wireframemotion spatial-parallaxpower spatial-parallaxinstrument laser-fire→The Stack
6s6
first render · fix pending
shared field
signature-3ddead_airgeneric_scene		resolve30.7–35.7scoalescenceicon·white-knockout♪ bed_out
The Stack
expected on screen: black 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 blacktreatment white-knockoutmotion coalescencepower coalescenceinstrument coalescence→The Stack

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 stack: Notion is a lovely place to lose things, because its search only matches exact words. So we export the pages, embed them into vectors, and run semantic search. Now you find ideas by meaning, and it cites the exact page. (AI-assisted)
instagramThe Stack Notion search only matches exact words. Fix: Export the pages. Embed them into vectors. Run semantic search. Now you find ideas by meaning, with the page cited. #notion #rag #vectorsearch #knowledgebase #ai
linkedinThe stack this week: Notion. It is a beautiful place to lose information, because its search only matches exact words. So we export the pages, embed them into vectors, and run semantic search on top. Now you find ideas by meaning instead of exact phrasing, and the answer cites the exact page it came from. It becomes a search engine for your own head. Try it on one database: export it, embed it, and ask it something fuzzy.
xNotion search only matches exact words. So we export the pages, embed them into vectors, and run semantic search. Now you find ideas by meaning, with the page cited. temerarii.xyz
facebookThe stack this week: Notion. It is a lovely place to lose information, because its search only matches exact words. So we export the pages, embed them into vectors, and run semantic search. Now you can ask your notes a question in plain language and get the exact page back. Try it on one database.
threadsThe stack: Notion is a beautiful place to lose information, because its search only matches exact words. So we export the pages, embed them into vectors, and run semantic search. Now you find ideas by meaning, and it cites the exact page. Export one database, embed it, ask it something fuzzy.
pinterestTurn Notion into a search engine for your own notes. Notion search only matches exact words, so ideas get lost. The fix: export the pages, embed them into vectors, and run semantic search. Now you find ideas by meaning, not exact phrasing, with the source page cited. A practical knowledge-base and RAG workflow.
blueskyNotion search only matches exact words. So we export the pages, embed them into vectors, and run semantic search. Now you find ideas by meaning, with the page cited.
youtubeTitle: Turn Notion Into a Search Engine: Export, Embed, Semantic Search Notion is a beautiful place to lose information because its search only matches exact words. We show how to export the pages, embed them into vectors, and run semantic search, so you can find ideas by meaning and get the exact page cited. A plain-language walkthrough you can run on one database.

Cross-links every lens is a view on this one record

→ Wireframe · scenes→ Calendar week→ Media (audience preview)→ Storyboard hub→ Day view→ Channel view