Checklist the per-video bar — engine/sim
100.0/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review longform-W47-Wed 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 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 7 scenes · 156.0s · 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 | 0–25.5s | spatial-parallax | icon·color | ♪ bed_in | Most events are expensive parties that end in a pile of business cards nobody calls. This week is about turning access into pipeline, and an event is just a room full of access if you run it right. Today you will learn to plan an event, capture who showed up, and follow up before the goodwill goes stale, with AI doing the boring half. We start before anyone walks in. on-screen: Event coordination that pays |
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · node-graph · spatial-parallax · icon·color logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape octaground whitetreatment colormotion spatial-parallaxpower summoninstrument summon→Event coordination that pays | |||||||
| 2 |  matches intent NumberedList template | teach | 25.5–49.3s | kinetic-build | icon·color | ♪ node_lock | The first move is not booking a venue; it is naming the exact thirty people you want in the room. Have Claude Code build that guest target from your customer type and your partner list, grouped by who you most want to meet. The model gives you names and why each one belongs. You design the event around those people, not the other way around. on-screen: Pick the room before the date |
expected on screen: white ground · a NumberedList panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape octaground whitetreatment colormotion kinetic-buildpower morphinstrument morph+laser→Pick the room before the datecurate items, nodes | |||||||
| 3 |  matches intent ChecklistCard template | teach | 49.3–72.69999999999999s | kinetic-build | icon·color | ♪ node_lock | An event with no record is a memory, not a pipeline. Use a simple sign-in form whose answers flow straight into a spreadsheet through the agent's MCP connection. Name, company, and the one thing they want. The model logs it live. When the night ends you do not have a stack of cards; you have a clean list the machine can already work with. on-screen: Capture every name at the door |
expected on screen: white ground · a ChecklistCard panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape octaground whitetreatment colormotion kinetic-buildpower morphinstrument morph+laser→Capture every name at the doorcurate items, nodes | |||||||
| 4 |  matches intent CodeWindow template | teach | 72.7–94.0s | kinetic-build | icon·color | ♪ node_lock | Not every guest is a lead, and pretending otherwise wastes your week. Have the agent read that sign-in list and sort it into three buckets: ready to talk, worth nurturing, and just here for the snacks. It uses the one thing each person said they wanted. Now your follow-up effort goes where it can actually turn into revenue. on-screen: Sort the room by intent |
expected on screen: white ground · a CodeWindow panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id CodeWindowvisual node-graphshape octaground whitetreatment colormotion kinetic-buildpower morphinstrument morph+laser→Sort the room by intentcurate codeLines, nodes, windowTitle | |||||||
| 5 |  matches intent JsonDiff template | teach | 94.0–116.7s | kinetic-build | icon·color | ♪ node_lock | The window after an event is short and most people sleep through it. Set the agent to draft a personal note to each ready-to-talk guest within a day, referencing the actual thing they said at the door. You read and send. A note that proves you listened beats a generic thank-you every time, and it lands while they still remember your face. on-screen: Follow up while it is warm |
expected on screen: white ground · a JsonDiff panel over a dimmed Signal Field · Lumen leads · node-graph · kinetic-build · icon·color logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual node-graphshape octaground whitetreatment colormotion kinetic-buildpower morphinstrument morph+laser→Follow up while it is warmcurate fileName, lines, nodes | |||||||
| 6 |  matches intent RankList template | proof | 116.7–136.9s | receipts-count | icon·color | ♪ node_lock | We plan our own gatherings with this exact flow: target the room, capture the door, sort by intent, follow up fast. It all runs from the same source file that builds our public office. No made-up attendance figures here, just the system you can watch at office dot temerarii dot xyz doing the unglamorous work. on-screen: We run our own room this way |
expected on screen: white ground · a RankList panel over a dimmed Signal Field · Lumen leads · receipts · receipts-count · icon·color logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape octaground whitetreatment colormotion receipts-countpower receiptsinstrument spotlight→We run our own room this waycurate rows, statsLabels | |||||||
| 7 |  matches intent shared field signature-3d | resolve | 136.9–156.0s | coalescence | icon·color | ♪ bed_out | Your next step is one small event, even a dinner for eight. Name the people first, set up the sign-in sheet, and have the follow-up ready before anyone arrives. That turns a nice evening into a pipeline. See how we do it at office dot temerarii dot xyz, then pick your eight. on-screen: Plan one small room |
expected on screen: white ground · octa hero in the shared Signal Field · Lumen leads · coalescence · coalescence · icon·color logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape octaground whitetreatment colormotion coalescencepower coalescenceinstrument coalescence→Plan one small room | |||||||
Format stack 1 aspects · same scenes[], re-cropped
16:9
1920×1080
X/Twitter · YouTube · LinkedIn video
Channels 2 destinations
YouTubeBlog
Social captions supplemental published copy · per channel (comp_id level)
youtubeEvent Coordination That Pays: Target the Room, Capture the Door, Follow Up Fast
Most events are expensive parties that end in a pile of business cards nobody calls. In this video we show how to plan an event, capture who showed up, and follow up before the goodwill goes stale, with AI doing the boring half.
The moves:
- Pick the room before the date. The first move is not booking a venue; it is naming the exact thirty people you want in the room. Have Claude Code build that target from your customer type and partner list, grouped by who you most want to meet. Design the event around those people.
- Capture every name at the door. An event with no record is a memory, not a pipeline. Use a simple sign-in form whose answers flow straight into a spreadsheet through the agent's MCP connection: name, company, and the one thing they want.
- Sort the room by intent. Have the agent read the sign-in list and sort it into three buckets: ready to talk, worth nurturing, and just here for the snacks. Your follow-up effort goes where it can turn into revenue.
- Follow up while it is warm. Set the agent to draft a personal note to each ready-to-talk guest within a day, referencing the actual thing they said at the door. You read and send.
The honest proof: we plan our own gatherings with this exact flow, target the room, capture the door, sort by intent, follow up fast. It all runs from the same source file that builds our public office. No made-up attendance figures, just the system at office.temerarii.xyz.
The takeaway: name the people first, set up the sign-in sheet, and have the follow-up ready before anyone arrives. Even a dinner for eight turns into a pipeline.
Keywords: event planning, lead capture, follow-up, spreadsheet, MCP, AI agent.