The Studio
An AI studio organised like a software company. Each department has its own skills, its own work queue, and only the context it actually needs.
One person decides. One desk keeps the day in order. Ten departments of specialists do the work.
1
One human. Answers the questions, reviews every mock, approves every gate.
1
Routes every new issue to the right department, keeps the day in order, and sets up each new product's repository and folder.
10
Ideation to Marketing. Each head plans the work and asks the CEO.
46
Claude sub-agents, each on the model that fits its job.
69
All the studio's written playbooks: how each head and specialist does the work.
11
Godot, ComfyUI, Fastlane, Firebase and more: what a department would otherwise buy in.
Why not just agentic coding?
Point a single agent at a whole app or game and the same ten problems show up. The studio is built to do the inverse of each one.
01 · Context
Agentic codingUnrelated work piles up in one context window. The model weighs all of it, so the output turns erratic: tasks get mixed together and it fixes problems that no longer exist.
The studio keeps context outside the model. GitHub issues hold the work, written handoffs carry the decisions, and each department loads only its own brief. Every session starts clean.
Unrelated context in, erratic output out.
Context window94% full
Each one starts from its own brief and holds only what its job needs.
Ten windows, each mostly emptyDesign is working on the chest tile
02 · Issues, not chat
Agentic codingThe work lives in a chat. Close it and the plan, the decisions and the reasons go with it.
Labels say who owns it, who needs to know and what is waiting on the CEO. Departments ask each other through sub-issues. Every decision is a comment, so the issue is the memory.
Add a buried treasure chest tile to World 1 #142
Chief of Staff routed it to Design and told Marketing
Design head asked Marketing in a sub-issue
Will the chest change the store screenshots? #143
CEO answered 2 questions and approved the prototype
Design head wrote the handoff to Engineering
Engineering head linked a pull request · merged, checks passed
03 · Departments and heads
Agentic codingOne agent wears every hat: it designs, codes, tests and markets with the same instructions.
A label routes the issue to one department. Its head plans the work, asks the CEO and hands each part to a specialist. Only that department's skills load, never all 69.
Loaded for this issueTold about it, loads nothingStays on the shelf
5of 69 loaded
04 · Short skills
Agentic codingGiant prompts and rule files load every time, whether the task needs them or not.
A skill is a one-page procedure. Its depth lives in reference files that load only when that step runs. A check runs after every skill edit, so none of them can quietly grow.
design-head / SKILL.md · 62 lines 1. Read the issue and the last handoff. 2. Ask the CEO, one card at a time. 3. Pick a direction → references/directions.md 4. Mock first, screenshots per state. 5. Write the handoff to the issue.
05 · Small handoffs
Agentic codingThe next task starts by inheriting the last task's entire conversation.
Every handoff is written back to the GitHub issue. The next department starts clean from that brief, instead of inheriting a massive conversation.
Design head commented · Handoff to Engineering
docs/spec/chest.mdart/painted/tiles/chest.pngLeft behindThree mock rounds, two rejected directions and every message in between.
06 · Approve before build
Agentic codingIt builds first and asks later, so you find out what it misunderstood after it has written it.
Before any work starts, the department either asks its questions or shows a prototype. Either way, the work waits on one person.
Design · question 2 of 3
Where can a chest be buried?
or

The ceo:review label holds the issue until the CEO answers.
07 · Borrowed expertise
Agentic codingIt only knows what the model knows, so the result looks like every other AI app.
Where someone has already written the best guide to a craft, the studio uses it instead of writing its own. Each one is loaded by the department that needs it, and nowhere else.
08 · Rules that can't be forgotten
Agentic codingAn instruction in the prompt gets forgotten halfway through, and nothing notices.
Hooks run on every action, whether the agent remembers the rule or not. Checks have to pass before the CEO is ever asked.
09 · Chief of staff, continue
Agentic codingYou are the scheduler. Every morning starts from scratch, steering turn by turn.
The CEO doesn't brief ten departments. The Chief of Staff reads the latest handoffs, checks GitHub, asks anything it needs, and keeps the work moving. Every session ends clean.
It routes new issues, then asks the CEO everything waiting on them, one multiple-choice question at a time.
One question: which departments work this session. The busiest unblocked queue is recommended, or run every department with work, in order.
The chosen heads run one after another on their own queues. Between heads, the Chief of Staff writes down where things stand.
With the handoff saved, the CEO clears the conversation and starts fresh through the Chief of Staff. Every session begins clean, and nothing is lost.
> /aiceo:chief-of-staff Routed 3 new issues: #142 Design, #145 Engineering, #147 Marketing 2 questions answered. Nothing else waits on you. Which departments should work this session? ❯ 1. Design, 4 ready (recommended) 2. Engineering, 3 ready 3. Marketing, 1 ready 4. All with work, in that order Design head: 3 issues done, 1 mock waiting for your review Handoff written to .factory/handoff.md Safe to /clear now. Then run /aiceo:chief-of-staff continue. > /clear > /aiceo:chief-of-staff continue Read the handoff. Next up: Engineering, 3 ready.
10 · The right model for each role
Agentic codingOne model for everything: too costly for routine work, not careful enough for the hard calls.
Like hiring, each seat in the company is matched to the work. The expensive judgement is saved for where it pays.
From people using it
“The aiceo tools and workflows are redefining AI development. By pulling everything into GitHub, it's easier and faster to plan and work on my projects, and it's made it possible to actively work on several at once without blowing up my usage limits.”
“Most AI setups drag the whole company into every task, and you pay for it in tokens. aiceo only sends the department whose job it actually is, with the few rules that matter right now. Everything lives on GitHub issues, so a session reads one issue instead of relearning the whole project.”
So far
None of this is new. People have organised teams this way for decades.
It turns out the same structure works remarkably well for AI agents too.