new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

Workflows

Knowing things is not the hard part.
Knowing the order is.

Every trade has a sequence: what gets settled before anyone builds, what nobody touches until the numbers agree, what has to pass before it goes out. It takes a year to learn, it lives in whoever learned it, and it leaves when they do. A workflow is that sequence written down once — and walked by the agent you already pay for.

Write oneSee what is published

A step carries four things

Together they are the difference between an instruction an agent interprets and one it can be held to.

The brain

What to read before writing anything — material that sat an exam and has a score, not something remembered from training.

The prompt

What to ask it, in that brain's own words. Those are the words it can actually find.

The rules

What always and never holds while the step runs. "Never hand-edit a generated file." They survive after the question is answered.

The check

How the agent knows the step is done. A command that exits zero, not a feeling.

Routes worth writing

Shapes, not listings — the published ones are further down. The test is simple: if your team repeats a sequence and argues about it, that sequence is a route.

Game studio

Ship a slot to a platform that reviews it

spec → math → books → front end → approval

Web team

Move a framework major version without breaking a Friday

read the migration → inventory → codemod → tests → staged rollout

Solo developer

Take a prototype to something with saves and settings

save format → versioning → scene flow → input → build

Agency

Onboard a codebase nobody here wrote

map → conventions → run it → first change → write back

Anyone with an API

Write documentation an agent can actually follow

audit → shape → examples → verify → publish

Research

Turn a week of reading into a brief somebody can act on

sources → extract → contradictions → brief → review

A published route, drawn from itself

Not a screenshot — this is read from the route, so what you see is what your agent gets.

StartWhat the user asked for
Step 1Concept, theme and the one-page specreads mozg/slot-design-presentationthe spec states RTP, volatility, max win and every feature, and the user has agreed to it
Step 2Math model and modesreads mozg/stake-engine-math-sdkrun.py completes and the simulated RTP for every mode is within 0.1% of the spec's target
Step 3Books, lookup tables and optimizationreads mozg/stake-engine-math-sdklibrary/publish_files/ exists for every mode and its lookup tables reproduce the target RTP
Step 4Math against Stake's own requirementsreads mozg/stake-engine-approvalevery number in the math requirements page has a measured value from the simulation beside it
Step 5RGS lifecycle and replayreads mozg/stake-engine-rgs-apia full round completes against the RGS and the same round replays identically from its book
Step 6Front end and the event contractreads mozg/stake-engine-web-sdkevery event kind present in the books is handled, and an unknown event fails loudly in development
DoneThe thing exists, and its checks passed

A Stake Engine slot game, end to end12 steps, with every prompt and rule

Your agent runs it. Nothing runs here.

One command

/mozg:build handle/route — from Claude Code, Codex, Cursor, anything that speaks MCP.

It checks the shelf first

A route names the brains it needs. Missing or unbought ones are named before any work starts, not at step nine.

It can go back

A failing check sends the agent back a step. That is judgement at runtime, which no drawn arrow can express.

It reports

Which step found nothing, which check did not pass. The author then fixes the route from data rather than memory.

/mozg:build mozg/stake-engine-game

Why this is a list and not a canvas of boxes

Visual builders are good at what they do — wiring services together, where every branch is known before it runs. A build is not that. Nobody can draw the arrow for "the RTP came out at 94.2%, go back two steps and reweight"; you can only write the check and let something with judgement decide. So a route here is an ordered list with a check on every step, and the judgement belongs to the agent walking it. The day real branches are needed, that is a graph — and a graph is a different product.

Published routes

A Stake Engine slot game, end to endConcept, math, books, RGS, front end, motion, art, compliance, then the publish gates — each step on the brain that knows it.mozg/stake-engine-game · 12 steps · 10 brainsOpen

Write down the order once.

Then it runs from anyone's terminal, on the same material, with the same checks — including the terminal of whoever joins next month.

Build a workflow