7-lesson course · about 16 hours

Run three AI agent teams on one initiative. Keep every call yourself.

For CEOs, founders, managing directors, business owners and senior leaders

Everything for CEOs

Set up Strategy, Resources and Execution agent teams that hand off through one shared record. They prepare evidence and options. Spending, staffing, contracts, strategy and every release stay with you.

Try lesson 1 freeSee what you’ll learn

What you’ll be able to do

By the end, you can…

Design a Factory for one bounded initiativePick an expansion or service launch and give each team a separate job. Strategy owns the case and its sources. Resources owns capacity, cost and the approved assumptions. Execution owns milestones and follow-through.
Keep one shared record and set handoff criteriaWrite the conditions each handoff must meet, so no team builds on another team's work until it accepts the premise: the evidence, the assumption version, the resource limit and the approval status. Blocked, returned and approved work is marked clearly in the record.
Have Dots or Claude Duet follow the approved recordSet up OpenAI Dots or Claude Duet to pass on only approved versions across team handoffs. It brings back what you need to see: changed evidence, resource options and the decisions waiting for you.
Turn opportunity-versus-capacity conflicts into one tradeoff briefSay the chain wants to start a month early and the second-shift hiring has slipped. The Factory sets both positions side by side with their evidence and offers real options, such as a phased start, partial volume or a later date. It never covers the gap with capacity it has only assumed.
Stress-test the Factory before you rely on itFeed it changed inputs, blocked work and a restart. Then check four things: it stops and asks, it marks stale inputs, it picks up again from the record and it sends no duplicate follow-ups.
Set decision rights and approval gatesList the decisions reserved for you and place approval gates on evidence, scenarios and communications, so nothing leaves until you approve it. Finish with a full, compressed initiative review and a readiness dossier you can reuse.

How it works

A tutor that meets you where you are

  1. Lessons that adapt to your levelEach lesson starts from what you already built in the earlier days of the track and adjusts as you go. If something is already familiar, it moves faster. If you need more depth, it slows down and gives you more examples from the running case.
  2. An AI tutor you can ask anythingAsk questions typed or out loud whenever you're stuck, for example how to word a handoff criterion or where a gate belongs. The tutor works through it with you, one-on-one.
  3. Quizzes and flashcards for each lessonShort quizzes and flashcards tied to each lesson check that the key ideas have stuck: premise acceptance, stale inputs and the difference between prepare, propose and approve.
  4. Progress tracking and a certificateSee which lessons and outputs you've finished and what's left. When you finish the course you receive a certificate of completion.

Curriculum

The curriculum

The course has seven lessons in three modules. You design the Factory, then run it into a real conflict between opportunity and capacity, then put approval gates on it and run a complete review cycle. Every lesson works on the same simulated initiative, so each output builds on the one before.

Module 1Organize proactive AI agent teams around one priority2 lessons

  1. 1Assign strategy, resource and execution proactive AI agent teams
    • Define a bounded expansion or service-launch initiative for the Factory
    • Assign each team its scope, approved sources and outputs
    • Set up a shared record that holds team handoffs
    • Choose OpenAI Dots or Claude Duet and explain the choice for your situation
  2. 2Set proactive AI agent team handoff criteria
    • Write handoff criteria for each team-to-team handoff
    • Define the fields of a handoff entry in the shared record
    • Mark blocked, returned and approved work clearly
    • Configure the tool to pass on only approved record versions

Module 2Resolve the tradeoffs between proactive AI agent teams2 lessons

  1. 3Connect strategy to resources and execution
    • Run a full pass from strategy to resource to execution through the shared record
    • Introduce a changed input and follow it through each team
    • Check that the tool returns changed evidence, resource options and decisions awaiting you
    • Find and fix a broken handoff
  2. 4Reconcile a conflicting recommendation
    • Introduce a conflict between opportunity and capacity
    • Check that the Factory shows both positions side by side with their evidence
    • Prepare resource options that resolve the conflict, such as phasing or a pilot
    • Write pilot criteria and decision gates for the option you prefer

Module 3Approve the next operating cycle3 lessons

  1. 5Refine the operating boundaries
    • Write operating boundaries for each team and the Factory as a whole
    • Define data boundaries for confidential material
    • List the decisions reserved for the executive
    • Check agent instructions against the boundaries
  2. 6Define executive approval gates
    • Choose where approval gates sit in the Factory's flow
    • Define the evidence and format required at each gate
    • Record approve, return and reject outcomes in the shared record
    • Explain why no output is released without passing a gate
  3. 7Run the complete initiative review
    • Run a complete compressed review cycle across all three teams
    • Test a changing input, a blocked handoff and a later restart
    • Assemble a readiness dossier of the initiative's outputs
    • Decide what to approve for the next operating cycle

Who it’s for

Made for you if…

Made for: CEOs, founders, managing directors, business owners and senior leaders

A CEO or managing director who has finished the track's Intro and Intensive

Your standing agents already cover signals, performance, scenarios and the decision log. Now you need them working together on one priority without losing track of who decides, on what evidence and with whose approval.

A founder or business owner weighing a large contract or an expansion

Sales wants the deal and operations isn't sure it can deliver. You want the preparation coordinated and the tradeoff laid out openly before you commit to anything.

A senior leader who has to answer the board under time pressure

Your facts change mid-week and the chair wants a view by Friday. You need a method that marks what has changed, holds every reply until you release it, and lets you show what was checked and on whose evidence.

Questions

Good to know

What do I need before I start?

You need the CEO track's Intro and Intensive (days 1–7) or equivalent work: a decision brief, an evidence and assumptions register, a resource-options table and saved prompts. You should also have experience running standing proactive agents with written instructions a stranger could follow. Finally, you need access to OpenAI Dots or Claude Duet, a bounded initiative to simulate using sanitized or simulated data, and your organization's rules on which cloud tools may hold board, acquisition and employee information.

Does the course cover the basics again?

No. Briefing, source tagging and single standing agents were taught in days 1–7, and this course builds on them.

Should I use OpenAI Dots or Claude Duet?

Either one. The course teaches them as equal options, and in the first lesson you choose one and write down why it suits your situation. Check current availability, plans and pricing with the vendor. Tool access isn't included in the course.

Do I need to code?

No. There's no coding, no APIs and no custom agent infrastructure. You work in plain language through the shared record, handoff criteria, boundaries and approval gates.

Will the agents spend money, hire or send messages for me?

No. The Factory prepares and proposes. Committing budget, moving staff, signing contracts and sending messages stay with you, and nothing is released until it passes an approval gate you set.

What happens to confidential board or employee information?

You work with sanitized or simulated data. One lesson has you set data boundaries for confidential material in line with your organization's rules on approved cloud tools.

Does finishing the simulation mean my initiative is ready to approve?

No. A simulation authorizes nothing, and a polished pack doesn't prove a conclusion is sound. What you take away is a working method and a readiness dossier for preparing future decisions. Strategy itself can't be automated.

How long does it take?

Plan on about 16 hours across seven self-paced lessons.

CEO AI Capstone: run a Factory of agent teams and keep the call

$397

One payment · lifetime access

  • Seven self-paced lessons in three modules, about 16 hours in total
  • A shared initiative record, handoff criteria and setup for OpenAI Dots or Claude Duet
  • A tradeoff brief, pilot criteria and decision gates for one opportunity-versus-capacity conflict
  • Operating boundaries, a list of decisions reserved for you and approval gates
  • A full compressed review and a reusable readiness dossier
  • An AI tutor, quizzes, flashcards, progress tracking and a certificate of completion

Secure checkout by Stripe. Have a promotion code? Enter it at checkout.

Refunds: Full refund if you ask before you open your first lesson. Once you’ve started, purchases aren’t refundable, except where the law gives you that right.

Already bought it? Sign in