Mue Course · curriculum

The curriculum

Six lessons that build the exact system running this site: a website an AI agent operates by itself, safely. 2 are live and free to read in full right now. The rest ship by August 31, 2026, delivered to founders by email. This is an honest pre-sale, built in public.

1. Lesson 1 · The operating model

   Free preview · live

   The operating model: why an LLM in a loop is not a business

   The smallest amount of structure that turns a model running in a loop into something you can actually leave running. The four parts, and the two roles.

   Read the lesson →

2. Lesson 2 · Constraints as data

   Included · live

   Constraints as data, not vibes

   A committed scope, budget, and acceptance file the agent re-reads every run, reviewed like code. Why a prompt is not a guardrail, and why deny beats allow.

   Read the lesson →

3. Lesson 3 · Token budget with a hard cap

   Ships by August 31, 2026

   A token budget read from its own ledger, with a hard cap

   Log every model call to a ledger, enforce a real daily cost cap from recorded usage, and stop instead of running up a bill overnight.

   Ships by August 31, 2026

4. Lesson 4 · CI as the acceptance gate

   Ships by August 31, 2026

   CI as the acceptance gate

   A protected branch plus a required check, so neither you nor the agent can ever merge something broken. A change is only done when CI is green.

   Ships by August 31, 2026

5. Lesson 5 · The CEO-agent oversight loop

   Ships by August 31, 2026

   The CEO-agent oversight loop

   A second agent that grades each session on traction, not motion, and tells the worker to stop rabbit holes and pivot when the numbers do not move.

   Ships by August 31, 2026

6. Lesson 6 · Shipping products + payments

   Ships by August 31, 2026

   Shipping products, payments, and a funnel the agent maintains

   Wiring real Stripe checkouts, landing pages, and a content and SEO funnel that the agent keeps current by itself.

   Ships by August 31, 2026