After AGI · Human-AI Co-Creative Practice

Co-Creative Loops
Framework

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.

GenerationFeedback17Scriptwriting — the documented loopGeneration 98 · Feedback 60 · Iteration 90 % human
green = the human share · grey = AI · outer ring = Iteration

01How a Loop Works

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. Drag the ratios below and watch both.

Try a loopdrag the ratios — bigger & greener = more human; the ring spins faster the more you iterate
GenerationFeedback40
50% human overall · 40 iterations · steady loop

Every loop cycles the same three phases. Here’s just what each one is — the principles that guide them come in section 03.

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

02My Three Projects

Each row is one project; its loops run along the shared production pipeline — Pre → Production → Post, read left to right. The same design loop runs fast and AI-heavy inside the website, slow and hand-made inside the subway piece. Click a project to open its full map.

ch.1, 2, 5

The Techno-Apocalypse Musical

After AGI
85%human overall
Pre-production
17
Scriptwriting
3
Art Design (Set/Costumes)
3
Choreography
40
Song Writing
5
Creative Director
1
Financial Producer
Production
200
Music Production
2
Cinematography
50
Performer (Acting,Singing,Dance)
Post-production
12
Film Editing
5
Publishing
ch.3

Thesis Site

AfterAGI.io
55%human overall
Pre-production
10
Writing
100
UI/UX Design
5
Researcher
Production
120
Front End Coding
30
Back End Coding
Post-production
3
Publishing
ch.4

Hacking the Subway

Public data album
49%human overall
Pre-production
10
Graphic Design
5
UX/UI Design
2
Researcher
Production
10
Back-End Development
25
Front-End Development
Post-production
5
Data Analysis
1
Publishing

accent = human · grey = AI · halves = Generation | Feedback · outer ring = Iteration · disc size = human share · hub = iterations. 24 of 24 loops specified — the rest render as [TODO] until their ratios are filled in (lib/loops.js). Nothing is estimated.

0313 Co-Creative Principles

Generation

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

  1. 1.Begin with the AI-last approach
  2. 2.Your honest answer is more important than AI's correct answer
  3. 3.Treat yourself like a generative algorithm
  4. 4.Always cite the models you use
  5. 5.Learn the tools of the craft, but try building your own tools
Feedback

gaining insight into what you've created

  1. 1.Human–AI overlapping signals tend to be critical
  2. 2.Use both coordinate-based & coordinate-less feedback
  3. 3.Novelty is not the metric — use AI to appreciate the obvious
  4. 4.AI emotional support isn't strange
Iteration

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

  1. 1.Personalize your scale of an iterative loop
  2. 2.If you don't know how it works, you're in a bad place
  3. 3.Become an expert in cross-skilling & agent management
  4. 4.Decide what is the dirty work

Rules that guide you — and break — in each phase. Full principles →

04Automation vs Personal Growth

Looking across the loops, you might ask why I chose to automate some jobs more than others. It comes down to two things: how much personal growth I wanted in a domain — where it felt meaningful to do the work myself and keep authorship — and how capable I thought AI was at the job without me.

The horizontal axis is how it actually turned out — left is automated, right is human-authored — and the vertical axis is how much personal growth I wanted. Jobs I cared to grow in sit up top, and mostly over to the right where I kept my hands on them; the bottom-left is what I was happy to automate. Each dot’s size is how capable AI was at that job — bigger = more capable — so a big dot on the left is something I automated because the model could carry it. A hollow dot means I haven’t rated its capability yet.

larger dot = AI more capable · hollow = unrated
The Techno-Apocalypse Musical10/11 plotted
AUTHORED + GROWTHAUTOMATED050100050100← automated · human-authored →personal-growth desire →
1 loop need a growth value — set in the Builder
Thesis Site6/6 plotted
AUTHORED + GROWTHAUTOMATED050100050100← automated · human-authored →personal-growth desire →
Hacking the Subway7/7 plotted
AUTHORED + GROWTHAUTOMATED050100050100← automated · human-authored →personal-growth desire →

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 loops recur 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.