AISeriesMaker

The plan limits behind an AI series

Scaling notes: planning around plan limits

The notes cover estimating throughput, choosing between fast and slow lanes, storage and deletion, and working with a team. As of 2026-09-25.

What sits in this sheetShort notes on planning an AI series around the limits tools publish, grounded in the sheet. The sheet holds 11 pages.SheetScaling notes11 pagesA pageOne limit or question, from published pages.A readingPage address and reading day.
Fig. 1 Pages in the sheet all point back here.

Every note draws its examples from the sheet and links each back to the tool it comes from.

No tool was run; the notes rest on the published limits alone.

Read them while planning episodes, before the limits decide the schedule for you.

Each note takes one decision a series maker faces, which lane to use, where files should live, how to split a season, and sets the published limits of several tools beside it so the choice can be made with the numbers in view.

1Pages in this sheet

2Making the series in practice

Limits aside, the series work behind “Scaling notes” is described in SceneMixer's guides like this:

That is SceneMixer's core design: characters live in a persistent asset library with locked reference art, and every segment that features a character is generated against those references — same face in episode 1 and episode 50.

SceneMixer, The AI Micro Drama Production Pipeline — “Can AI keep the same actors across 50 episodes?” (read 2026-10-13)

The longest an episode may run: 240 seconds for Short Drama, 300 for TV Series, none for Film.

SceneMixer, Short Drama, TV Series or Film — “What is the episode cap?” (read 2026-10-13)

3Other sheets