Growth & Performance Marketing — social-W38-Tue-1

post social-W38-Tue-1kind threadweek W38date 2026-09-22campaign thread · Tuepillar staff_trainingbeat Tueasset videoduration 63.2sground redscenes 9

Checklist the per-video bar — engine/sim

86.6/100

plain languagevo coverageno dead airuniquenesscaption fitcompletenesscleanliness

quantitative quality · weights learn from your reviews (engine.sim.memory review social-W38-Tue-1 good|bad)

⚠ 3 flag(s) — not yet ship-ready: copy_genericdup_sequence_across_assetsdup_set_across_assets · see docs/strategy/VIDEO-CHECKLIST.md

Composition comp · template family · expected output

composition SceneReelfamily / template SignalFieldReel

9:16 Reelpending1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending

render pending — silent master not yet on disk

expected output: 0/7 rendered — same matrix the /media preview surfaces for this asset.

Composition layer × scene 9 scenes · 63.2s · comp_id + rendered still + tier + the script

#	Layer (comp_id · still · tier)	Beat	Timecode	Motion	Logo	Audio	VO / on-screen / caption
1	still pending matches intent shared field signature-3d	open	0–6.6s	spatial-parallax	icon·liquid-chrome	♪ bed_in	Old way: AI sat behind a wall and only the big labs could touch the actual model. on-screen: AI was a black box
	expected on screen: red ground · knot hero in the shared Signal Field · Magister leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape knotground redtreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→AI was a black box
2	still pending matches intent shared field signature-3d	hook	6.6–12.5s	kinetic-build	icon·white-knockout	♪ node_lock	Here is what changed: the model now answers any plain-text instruction through a simple call. on-screen: The wall is gone
	expected on screen: red ground · knot hero in the shared Signal Field · Magister leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape knotground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→The wall is gone
3	still pending matches intent NumberedList template	teach	12.5–20.6s	kinetic-build	icon·liquid-chrome	♪ node_lock	New way: write your instruction as a prompt, send it to the model with a key, and read the answer back. on-screen: Wrap a prompt in an API
	expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Magister leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape knotground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Wrap a prompt in an APIcurate items, nodes
4	still pending matches intent RankList template	proof	20.6–26.900000000000002s	receipts-count	icon·white-knockout	♪ node_lock	Now any tedious reading or sorting task gets a tireless clerk that costs cents per run. on-screen: A clerk that never sleeps
	expected on screen: red ground · a RankList panel over a dimmed Signal Field · Magister leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape knotground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→A clerk that never sleepscurate rows, statsLabels
5	still pending matches intent LogStream template	diff	26.9–34.199999999999996s	crossfade-8f	icon·liquid-chrome	♪ node_lock	A clever demo is not a product. The work is the dull part: the checks, the retries, the guardrails. on-screen: A demo is not a system
	expected on screen: red ground · a LogStream panel over a dimmed Signal Field · Magister leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id LogStreamvisual codeshape knotground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→A demo is not a systemcurate codeLines, rows
6	still pending matches intent ChecklistCard template	teach	34.2–41.900000000000006s	kinetic-build	icon·white-knockout	♪ node_lock	Tell the model to answer only in a fixed format, so the next step in your code can trust it. on-screen: Constrain the output
	expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Magister leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape knotground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Constrain the outputcurate items, nodes
7	still pending matches intent StatScoreboard template	proof	41.9–48.5s	receipts-count	icon·liquid-chrome	♪ node_lock	A locked output turns a chatty model into a part you can wire into a real pipeline. on-screen: Structured output is reliable
	expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Magister leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape knotground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→Structured output is reliablecurate pillar, stats, statsLabels
8	still pending matches intent PipelineMap template	step	48.5–55.5s	kinetic-build	icon·white-knockout	♪ node_lock	Your step: pick one task you read by hand daily and wrap it in a single prompt-and-key call. on-screen: Automate one boring task
	expected on screen: red ground · a PipelineMap panel over a dimmed Signal Field · Magister leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id PipelineMapvisual pipelineshape knotground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Automate one boring taskcurate stages, steps
9	still pending matches intent shared field signature-3d	resolve	55.5–63.2s	coalescence	icon·liquid-chrome	♪ bed_out	Now AI is a quiet utility, not a mystery. The Big T-M wires it into the boring work that pays. on-screen: AI as a quiet utility
	expected on screen: red ground · knot hero in the shared Signal Field · Magister leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape knotground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→AI as a quiet utility

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)

tiktokAI is not a black box anymore. Write your instruction as a prompt, send it with a key, lock the output format. Wire it into real work. (AI-assisted) #ai #automation #api

instagramThe wall around AI is gone. Prompt in. Answer out. Lock the format. Wire it into work. #ai #automation #api #aitools #tech

linkedinAI used to sit behind a wall only big labs could reach. Now the model answers any plain-text instruction through a simple call. The practical move: write your instruction as a prompt, send it with a key, and force the output into a fixed format so the next step in your code can trust it. A clever demo is not a product; the real work is the dull part, the checks, retries, and guardrails. Pick one task you read by hand every day and wrap it in a single call.

xAI is not a black box. Write the instruction as a prompt, send it with a key, lock the output format, wire it into real work. Method:

facebookAI used to be a black box only big labs could open. Now you send a plain-text instruction with a key and read the answer back. Lock the output format so your code can trust it. Comment for the starter call.

threadsAI is not a mystery box anymore. Write your instruction as a prompt, send it to the model with a key, and force the answer into a fixed format so your code can trust it. The clever demo is the easy part. The real work is the checks and retries around it.

pinterestAI automation guide: how to call an AI model with a prompt and an API key, lock the output format, and wire it into real workflows. Automate the boring reading and sorting tasks. AI tools, automation, API, tech tips.

blueskyAI is not a black box. Write the instruction as a prompt, send it with a key, lock the output format, wire it into real work. Method:

youtubeAI Is Just an API Now: Wrap a Prompt, Lock the Output, Automate the Boring Work AI used to sit behind a wall. This shows how to call a model with a prompt and a key, force the output into a fixed format your code can trust, and build the unglamorous checks and retries that turn a demo into a real system. AI, automation, APIs. AI-assisted production.

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

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