engine.sim.memory review longform-W26-Tue good|bad)| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 | ![]() matches intent shared field signature-3d | open | 0–24.5s | spatial-parallax | icon·liquid-chrome | ♪ bed_in | If it works on us, it works for you. Today is creative conception, which is a fancy way of saying: where the idea comes from. Most agencies treat the idea like lightning, something that strikes a genius in a room. We treat it like a process you can run on purpose. Today I will show you how we generate and pick ideas without waiting for a mood. on-screen: Ideas, not vibes |
expected on screen: red ground · tetra hero in the shared Signal Field · Nexus leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape tetraground redtreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→Ideas, not vibes | |||||||
| 2 | ![]() matches intent NumberedList template | teach | 24.5–48.3s | kinetic-build | icon·white-knockout | ♪ node_lock | First move: do not ask a model for ideas cold. Give it your brand rules file first, the same plain text I keep talking about. Then ask for ten angles on one topic. Because it knows your voice and your banned words, the ten ideas come back already in your lane. A blank prompt gives you generic. A prompt with your rules gives you yours. on-screen: Feed the model your real rules |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Nexus leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape tetraground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Feed the model your real rulescurate items, nodes | |||||||
| 3 | ![]() first render · fix pending ChecklistCard templatecustom_element_dup | teach | 48.3–72.4s | kinetic-build | icon·liquid-chrome | ♪ node_lock | Second move: do not take the first idea. We ask the agent to attack its own list, to say which ideas are tired and why. This is just a second prompt: be the critic, kill the weak ones. The model is honest when you tell it to be. You end the round with three ideas that already survived a fight, instead of one idea nobody questioned. on-screen: Make it argue against itself |
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Nexus leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape tetraground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Make it argue against itselfcurate items, nodes | |||||||
| 4 | ![]() matches intent TerminalRun template | teach | 72.4–94.4s | kinetic-build | icon·white-knockout | ♪ node_lock | Third move: anchor each idea to something real you sell. We map every concept to a sub-service, like branding or print, so an idea is never just clever, it is useful. The agent keeps that map in a file. So a fun concept that teaches nothing gets cut. The idea has to do a job, or it does not ship. on-screen: Tie every idea to a service |
expected on screen: red ground · a TerminalRun panel over a dimmed Signal Field · Nexus leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id TerminalRunvisual node-graphshape tetraground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Tie every idea to a servicecurate nodes | |||||||
| 5 | ![]() matches intent StatScoreboard template | proof | 94.4–112.4s | receipts-count | icon·liquid-chrome | ♪ node_lock | The proof is the thing you are watching. Every day this week teaches a different facet, picked by this exact method, so no two days repeat. We did not brainstorm seven videos in a room. We ran the process. You can check that they are all distinct yourself, live. on-screen: This week ran on this method |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Nexus leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape tetraground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→This week ran on this methodcurate pillar, stats, statsLabels | |||||||
| 6 | ![]() matches intent shared field signature-3d | resolve | 112.4–133.3s | coalescence | icon·liquid-chrome | ♪ bed_out | Your next step: stop waiting for inspiration. Load your rules, ask for ten angles, make the model kill its own weak ones, then tie the survivors to what you sell. See a week of ideas built this way at office dot temerarii dot xyz. Inspiration is nice. A process you can run on a Tuesday is better. on-screen: Run ideas, stop waiting |
expected on screen: red ground · tetra hero in the shared Signal Field · Nexus leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape tetraground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→Run ideas, stop waiting | |||||||