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-build-log-W35-Wedkind threadweek W35date 2026-09-02campaign thread · Wedpillar performancebeat Wedasset videoduration 33.0sground whitescenes 6

Checklist the per-video bar — engine/sim

79.9/100
plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness
quantitative quality · weights learn from your reviews (engine.sim.memory review thread-build-log-W35-Wed good|bad)
⚠ 7 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 BuildLog
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 · 33.0s · comp_id + rendered still + tier + the script

#Layer (comp_id · still · tier)BeatTimecodeMotionLogoAudioVO / on-screen / caption
1s1
matches intent
shared field
signature-3d
open0–6.4sspatial-parallaxicon·3d-extrude♪ bed_in
Week thirteen. We shipped a content-gap report this week, every topic we haven't covered, ranked.
on-screen: Shipped: a content gap report
expected on screen: white ground · dodeca hero in the shared Signal Field · Mensor leads · node-graph · spatial-parallax · icon·3d-extrude logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape dodecaground whitetreatment 3d-extrudemotion spatial-parallaxpower summoninstrument summon→Shipped: a content gap report
2s2
first render · fix pending
DiffCard
templatedead_air
build6.4–11.4stype-onicon·color♪ node_lock
We used to guess our next topic, picking by gut and hoping it filled a real gap.
on-screen: Old way: guess what to write next
expected on screen: white ground · a DiffCard panel over a dimmed Signal Field · Mensor leads · code · type-on · icon·color logo · caption bottom-left
spec (the prompt): comp_id DiffCardvisual codeshape dodecaground whitetreatment colormotion type-onpower summoninstrument draw-on→Old way: guess what to write nextcurate codeLines, lines
3s3
matches intent
TerminalRun
template
diff11.4–17.6scrossfade-8ficon·color♪ node_lock
It broke on matching. Two posts about the same thing read as a gap because the titles differed.
on-screen: What broke: it counted near-dupes
expected on screen: white ground · a TerminalRun panel over a dimmed Signal Field · Mensor leads · code · crossfade-8f · icon·color logo · caption bottom-left
spec (the prompt): comp_id TerminalRunvisual codeshape dodecaground whitetreatment colormotion crossfade-8fpower morphinstrument morph→What broke: it counted near-dupescurate codeLines
4s4
matches intent
CheatSheet
template
step17.6–23.0skinetic-buildicon·color♪ node_lock
Now the gap report writes the roadmap. Next, we have it draft the outlines too.
on-screen: Next: auto-draft the outlines
expected on screen: white ground · a CheatSheet panel over a dimmed Signal Field · Mensor leads · pipeline · kinetic-build · icon·color logo · caption bottom-left
spec (the prompt): comp_id CheatSheetvisual pipelineshape dodecaground whitetreatment colormotion kinetic-buildpower throwinstrument laser-trace→Next: auto-draft the outlinescurate points, stages, steps, uses
5s5
first render · fix pending
StatScoreboard
templatedead_airgeneric_scene
proof23.0–28.0sreceipts-counticon·color♪ node_lock
Build Log
expected on screen: white ground · a StatScoreboard panel over a dimmed Signal Field · Mensor leads · receipts · receipts-count · icon·color logo · caption bottom-left
spec (the prompt): comp_id StatScoreboardvisual receiptsshape dodecaground whitetreatment colormotion receipts-countpower receiptsinstrument spotlight→Build Logcurate pillar, stats, statsLabels
6s6
first render · fix pending
shared field
signature-3ddead_airgeneric_scene
resolve28.0–33.0scoalescenceicon·3d-extrude♪ bed_out
Build Log
expected on screen: white ground · dodeca hero in the shared Signal Field · Mensor leads · coalescence · coalescence · icon·3d-extrude logo · caption bottom-left
spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape dodecaground whitetreatment 3d-extrudemotion coalescencepower coalescenceinstrument coalescence→Build Log

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)

tiktokBuild log: we shipped a content-gap report, every topic we haven't covered, ranked. It broke on matching, two posts on one idea read as a gap. Now it writes the roadmap. Next: it drafts the outlines too. (AI-assisted)
instagramBuild log. Shipped: a content-gap report. Every topic we haven't covered, ranked. What broke: near-dupes counted as gaps. Fixed. Now it writes the roadmap. Next: auto-draft the outlines. #buildinpublic #contentstrategy #seo #automation #marketingops
linkedinBuild log. This week we shipped a content-gap report: every topic we haven't covered yet, ranked by opportunity. We used to guess our next topic. What broke: it counted near-duplicates as gaps, because two posts about the same thing had different titles and read as separate misses. The fix was matching on meaning, not titles. Now the gap report writes the roadmap. Next, we have it draft the outlines too. That's the build, broken parts included.
xBuild log: shipped a content-gap report, every topic we haven't covered, ranked. It broke counting near-dupes as gaps. Fixed the matching. Now it writes the roadmap. Next: drafting outlines. temerarii.xyz/build
facebookBuild log: this week we shipped a content-gap report that ranks every topic we haven't covered. It broke at first, two posts about the same thing read as a gap because the titles differed. We fixed the matching, and now the report writes our roadmap. Next up: having it draft the outlines too. Follow the build at temerarii.xyz/build.
threadsBuild log. We shipped a content-gap report this week: every topic we haven't covered, ranked. It broke on matching, two posts about the same thing read as a gap because the titles differed. Fixed that. Now the report writes the roadmap. Next, it drafts the outlines too.
pinterestBuild log: how we built a content-gap report that ranks every uncovered topic. The bug: it counted near-duplicate posts as gaps because the titles differed, so we matched on meaning instead of titles. Now the report writes the content roadmap, and next it will draft the outlines. Content strategy automation, building in public.
blueskyBuild log: shipped a content-gap report, every topic we haven't covered, ranked. It broke counting near-dupes as gaps. Fixed the matching. Now it writes the roadmap. Next: drafting outlines.
youtubeTitle: Build Log, A Content-Gap Report That Writes Our Roadmap This week we shipped a content-gap report: every topic we haven't covered yet, ranked by opportunity, instead of guessing our next post. Then it broke. It counted near-duplicates as gaps because two posts about the same idea had different titles and read as separate misses. The fix was matching on meaning, not titles. Now the gap report writes the roadmap, and next we have it draft the outlines too. The build, broken parts included.

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