After AGI · Human-AI Co-Creative Practice

One loop
per job.

Between May 2025 and August 2026 I had 12,000 interactions with an LLM while making a musical, its music, a website, a subway installation, and a film. This framework is what survived: a way to see exactly where the machine was in the work — and to keep your authorship where you want it.

GenerationFeedbackScriptwriting — the documented loopGeneration 100 · Feedback 50 · Iteration 100 % human
green = the human share · grey = AI · outer ring = Iteration
12,000 interactionsMay 2025 Aug 20263 phases13 principles

01The Co-Creative Loop

Each project has multiple loops. Each loop corresponds to one job within a project. A musical carries loops for writing, design, music, choreography, film, publishing, direction.

Each loop breaks its job into three phases — Generation, Feedback, and Iteration — and each phase has a ratio of human vs. AI involvement.

Size — the averaged ratios set the size of a loop. The bigger the loop, the more human.

Speed — how many times the job’s output was iterated across the project’s timeline. More iterations, faster loop.

02Three phases

Generation

making original work — ideas and first drafts, your authorship behind it

Feedback

gaining insight into what you've created

Iteration

changing existing work on new insight; planning what's left to make or cut

0313 principles

Rules that guide you — and break — in each phase of a loop: 5 for Generation, 4 for Feedback, 4 for Iteration — from “Begin with the AI-last approach” to “Decide what is the dirty work.” Read all 13

04How it ran, project by project

05My Year in Data

Read across the built artifacts, the loop signatures diverge — the website a knot of large fast loops, the mini-musical a few small slow ones, the music in between. The same design loop recurs across projects at different settings, and that comparison is the clearest thing the data does that prose alone could not. See the year →

Ratios and definitions are authored claims from After AGI [v5], ch. 00. All counts are computed from the practice data — never invented.