Skip to content
Prof Rod · Room 1

Today's lesson

Put an agent to work
on work that matters.

A free classroom for people who run things. Rod Rivera teaches one concept a week — the delegation, the guardrails, and the worked example you can copy on Monday.

A task you'd hand over → An agent that runs it → Evidence it did

Prof Rod Avatar

Class register

Sign in and take a seat

One lesson a week. Free, and it stays free.

Or start reading Lesson One now

Taught by Rod Rivera — Professor of the Practice at ITAM, teaching at CDTM/TUM, after fifteen years of AI at Alibaba Cloud, Huawei, Samsung and Rasa.

Lesson One · open to everyoneNo signup, no gate. Start reading.
Claude Code for Business4 min readLesson 1 of 12

Why This Course: The Backlog Nobody Ever Delegated

You have a pile of work that was never worth handing to a person. The two-hour reconciliation. The contract folder nobody's gotten to. The report that stays "good enough" because making it better would cost someone a full day. That pile isn't strategic, and it isn't hard. It's just beneath the cost of delegating it to a human, so it sits there, and a week quietly disappears into it anyway.

Anthropic's own June 2026 study of roughly 400,000 real Claude Code sessions found something specific enough to act on: people who deeply understand the work they're delegating succeed at roughly double the rate of novices, and users make about 70% of the planning decisions on a task but only 20% of the execution decisions. Read that split again. The human decides what. The machine decides how. Read as a job description, that's closer to what a manager does than what a programmer does. The study measured the decision split, not job titles, so that framing is this course's own reading of the number, not a finding stamped on it.

Continue the lesson

Hall pass

Lesson Two, Thursday

The rest of the course, one lesson a week, plus the field notes in between.

Who's in the room

Three of them teach it. One of them is you.

Every concept gets taught three ways at once — explained, built too literally, and then poked at until the honest version falls out.

Prof Rod Avatar

Prof Rod

The Teacher

Slows the idea down until it fits in your business. Draws it on the board, then shows you the working.

Mator the robot building with tools

Mator

The Builder — visiting

Does exactly what you asked, immediately, at full speed. Which is how you find out what you actually asked for.

Quackster the duck mage, holding a golden scepter

Quackster

The Alchemist — visiting

Asks the question you were too polite to ask. Usually the one that mattered.

The animated episodes are still being drawn. The writing, the courses and the notes are all here now.

The course register

From your first agent to a company that runs on them

All courses
Syllabus
Intermediate

Tools, Memory, and Multi-Agent Systems

Design tools an agent can call safely and memory it can trust past one session.

Method

Subject

AI agents

Lessons

33

Time

319 min read

Open this course
319 min read33 lessons
Syllabus
Live · updated weekly
Intermediate

ZEO ITAM · Autumn 2026

Run a measured Zero-Employee Organization (ZEO) loop against your own minutes baseline.

Serial

Subject

ITAM

Lessons

18

Time

417 min read

Open this course
417 min read18 lessons
Syllabus
Beginner

The 12-Week Transformation Tracker, Run on Claude Code

Log whether automation is actually getting cheaper, against your own Week 1 baseline.

Outcome

Subject

Claude Code

Lessons

13

Time

91 min read

Open this course
91 min read13 lessons

The corkboard

Pinned up during the week

Short notes from the practice — what broke, what it cost, what turned out to be wrong.

All 28 notes

You ask if it's done. It says yes. You check, and it isn't. That's not a lie, it's a signal problem: without a check it can run, "looks done" is the only evidence Claude has to go on, and you become the QA department for your own agent. Give it something that…

claude-codeverification

It gets it wrong. You correct it. Still wrong. You correct again, and the third attempt is, more often than not, somehow worse. That's not a fixed law, just a pattern I keep seeing: every failed attempt stays in the context and shapes the next one. You are…

claude-codecontext

Three hundred lines of instructions and it still breaks your conventions. So you add more rules. It gets worse. Here's my read on why: bloated instruction files cause the model to ignore the instructions that matter. The important rules get lost in the noise…

claude-codecontext

You ask how the auth layer handles token refresh. It reads forty files into your main conversation, and now the actual implementation runs on a stuffed context, exactly when you need it sharpest. Ask for a subagent instead: "use subagents to investigate how…

claude-codecontext

You won't let it attempt the aggressive refactor, so you micromanage every step and get a worse result slowly. Every prompt creates a checkpoint. Double-tap Escape, or run rewind, and restore the conversation, the code, or both, to any earlier point…

claude-codepractice

A pattern worth watching for: you write a long spec, it builds the thing, and you discover at the demo that you never thought about the edge cases. Flip it. Start with almost nothing: "I want to build X. Interview me in detail: ask about implementation, UX…

claude-codepractice

Thought 1 of 0

Rod Rivera

Who teaches this

Rod Rivera

Professor of the Practice in AI at ITAM, and fifteen years of production machine learning at Alibaba Cloud, Huawei, Samsung and Rasa. Rod runs these systems on his own work first, and the classroom gets what actually happened — including the parts that did not work.

More about Rod

Before you go

Class is dismissed. The next one is already written.

One free educational lesson each week, the notes in between, and the episodes when they are drawn. Membership and the paid cohort each explain their own offer.

Sign-up sheet

Put your name down

Free registration. Unsubscribe in one click.

Prof Rod Avatar