Checklist the per-video bar — engine/sim
100.0/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review W34-always-on-beat-1 good|bad)✓ all static checks pass — one-focal/scene · tier-by-beat · one-track caption · colorway · cast+shape correct · no banned/fabricated. (audio + visual tiers verify on the rendered finals — Phase 2)
Composition comp · template family · expected output
9:16 Reelrendered1:1 Squarerendered16:9 Widerendered9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
expected output: 3/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 6 scenes · 44.3s · 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 | open | 0–7.6s | spatial-parallax | icon·liquid-chrome | ♪ bed in | Most AI advice sells you the sizzle and skips the steak, so today we hand you the whole playbook. on-screen: Most AI advice sells the sizzle |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape coneground redtreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→Most AI advice sells the sizzle | |||||||
| 2 |  matches intent shared field signature-3d | hook | 7.6–13.6s | kinetic-build | icon·white-knockout | ♪ — | The old reflex was to buy the shiniest tool and then go hunting for a problem it might solve. on-screen: Old way: buy the shiny tool first |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape coneground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→Old way: buy the shiny tool first | |||||||
| 3 |  matches intent NumberedList template | quote | 13.6–21.4s | kinetic-build | icon·liquid-chrome | ♪ — | Now we start with the business problem, name the exact task, then pick the model and a number we can measure. on-screen: Name the task. Pick the model. Measure |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Augur leads · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListshape coneground redtreatment liquid-chromemotion kinetic-buildpower summoninstrument shine→Name the task. Pick the model. Measurecurate items | |||||||
| 4 |  matches intent StatScoreboard template | proof | 21.4–28.299999999999997s | receipts-count | icon·white-knockout | ♪ — | We wire the tool in once through an MCP call, so the same step runs the same way every on-screen: Wire it once with an MCP call |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape coneground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→html-in-canvas-receiptscurate pillar, stats, statsLabels | |||||||
| 5 |  matches intent shared field signature-3d | hook | 28.3–35.2s | kinetic-build | icon·liquid-chrome | ♪ — | A demo impresses a room once. A repeatable playbook keeps paying out long after the applause stops. on-screen: A playbook beats a one-off demo |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · mark · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape coneground redtreatment liquid-chromemotion kinetic-buildpower laser-lockinstrument laser-trace→A playbook beats a one-off demo | |||||||
| 6 |  matches intent shared field signature-3d | resolve | 35.2–44.300000000000004s | coalescence | icon·liquid-chrome | ♪ bed out | Take the method, run it on your own work, and if you want the worked example it lives at temerarii.xyz. on-screen: Steal the method at temerarii.xyz |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Steal the method at temerarii.xyz | |||||||
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 12 destinations
LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBlueskyEmailSMSBlog
Social captions supplemental published copy · per channel (comp_id level)
tiktokMost AI advice sells you the sizzle. Here is the whole playbook. Start with the problem, name the exact task, pick a model, set one number you can measure, then wire it once with an MCP call so it runs the same way every time. (AI-assisted)
instagramMost AI advice sells the sizzle.
Here is the steak.
Name the task.
Pick the model.
Measure one number.
Wire it once with an MCP call.
A demo wows a room once. A playbook keeps paying out.
Worked example at temerarii.xyz
#aiplaybook #automation #mcp #buildinpublic #smallbusinessai
linkedinMost AI advice sells the sizzle and skips the steak.
The old reflex: buy the shiniest tool, then hunt for a problem it might solve.
What we do now:
1. Start with the business problem.
2. Name the exact task.
3. Pick the model and one number you can measure.
4. Wire the tool in once through an MCP call, so the same step runs the same way every time.
A demo impresses a room once. A repeatable playbook keeps paying out long after the applause stops.
Take the method, run it on your own work. The worked example lives at temerarii.xyz.
xMost AI advice sells the sizzle and skips the steak.
Name the task. Pick the model. Measure one number. Wire it once with an MCP call.
A demo wows once. A playbook keeps paying.
temerarii.xyz
facebookMost AI advice sells you the sizzle and skips the steak. Here is the whole playbook: start with the real problem, name the exact task, pick a model, set one number you can measure, then wire it in once with an MCP call so the step runs the same way every time. A demo wows a room once; a playbook keeps paying out. Grab the worked example at temerarii.xyz.
threadsMost AI advice sells the sizzle and skips the steak.
The playbook: start with the problem, name the exact task, pick the model, set one number to measure, then wire it once with an MCP call so it runs the same way every time.
A demo wows a room once. A playbook keeps paying out. Worked example at temerarii.xyz
pinterestA practical AI playbook for small business: how to use AI without buying the wrong tool. Start with the business problem, name the exact task, pick a model, set one measurable number, and wire it once with an MCP call so the step repeats reliably. Method-only AI workflow, automation, and MCP setup guide. Worked example at temerarii.xyz.
blueskyMost AI advice sells the sizzle and skips the steak.
Name the task. Pick the model. Measure one number. Wire it once with an MCP call. A demo wows once; a playbook keeps paying.
temerarii.xyz
youtubeTitle: A Practical AI Playbook: Name the Task, Pick the Model, Wire It Once
Most AI advice sells the sizzle and skips the steak. This is the whole playbook. The old reflex was to buy the shiniest tool, then hunt for a problem. Now we start with the business problem, name the exact task, pick the model and one number we can measure, then wire the tool in once through an MCP call so the same step runs the same way every time. A demo impresses a room once. A repeatable playbook keeps paying out. Take the method, run it on your own work. Worked example at temerarii.xyz.