Skip to content
AI AutomationSee plans

Menu

Taught by a Claude Certified AI System Architect

The AI agents course.

Build and train custom agents that run your business processes.

Pick one job in your business. Build an AI agent for it, teach it to work your way, and let it run on its own. No code needed.

What you'll learnSee the plans

From $79/mo. Both courses with Pro from $99/mo.

Until 31 December, every new student gets a 30-minute setup call with Luka.

Skill level
No code needed
Length
4 modules, 28 episodes
Opens
Module 1 now, one a week
Projects
Hands-on, for your business
Autonomous AI Automation: the course's name on a chip at the centre of a circuit board

The program map

From a process in your business to an agent that runs it.

28 episodes in 4 modules: 3 build the skills on one real job, the last is the projects you choose.

The program mapAutonomous AI Automation

  • The course
  • Mentorship, by application
  1. A track beside the course1 on 1 mentorshipA mentor beside you from the plan to the guardrails, on a process from your own business.See it on this page
  2. Module 1Understand AI agents7 episodes

    1. Module 1, episode 00What You'll BuildWhat you will have built by the end.See it on this page
    2. Module 1, episode 01What Is an AI Agent?What an agent is, and how it differs from a chat assistant and a workflow.See it on this page
    3. Module 1, episode 02What Is an AI Harness?The system around a model: goal, context, tools, memory, permissions and a loop.See it on this page
    4. Module 1, episode 03The Five Layers of AI HarnessFive ways AI is put to work, from chat to autonomous agents.See it on this page
    5. Module 1, episode 04AI Models: Local or Cloud?Where a model runs, and what that means for privacy, cost and capability.See it on this page
    6. Module 1, episode 05How an Agent WorksHow an agent works toward a goal: observe, decide, act, repeat.See it on this page
    7. Module 1, episode 06The AI Implementation MapFive questions to plan a process before you build.See it on this page
  3. Module 2Build a custom AI agent10 episodes

    1. Module 2, episode 07Set Up Your First Local AI AgentInstall an agent, give it a folder and a first task.See it on this page
    2. Module 2, episode 08How Agents ConnectThree ways an agent reaches your apps: an API, MCP and a command line.See it on this page
    3. Module 2, episode 09Connect Your Agent to GitHubKeep your agent's work in a private repository.See it on this page
    4. Module 2, episode 10Your First JobA meeting transcript becomes a brief and tasks on your board.See it on this page
    5. Module 2, episode 11What Is a Skill?Your way of doing a task, written down for an agent.See it on this page
    6. Module 2, episode 12Turn Your Procedure Into a SkillSave the job you just ran as a skill.See it on this page
    7. Module 2, episode 13What It CostsWhat a run costs, and four habits that keep it low.See it on this page
    8. Module 2, episode 14Set Your GuardrailsEight risks, and the guardrail for each.See it on this page
    9. Module 2, episode 15How I Edit Video With AILuka's editing skill, run on a raw clip and improved.4 partsFrom manual editing to an AI skill, Install the skill and run it, Review and improve the AI edit, Edit in DaVinci Resolve with an agentSee it on this page
    10. Module 2, episode 16Becoming AutonomousWhat an agent needs before it can run on its own.See it on this page
  4. Module 3Set up an autonomous AI agent8 episodes

    1. Module 3, episode 17What Is an Autonomous Agent?An agent that takes the work, does it your way and reports back.See it on this page
    2. Module 3, episode 18How an Autonomous Agent WorksIts parts, from the model to its permissions.See it on this page
    3. Module 3, episode 19Set Up Your First Autonomous AgentSet one up on a spare computer or in a sandbox.See it on this page
    4. Module 3, episode 20Add Guardrails and a Kill SwitchWhat it may do alone, when it asks, and how you stop it.See it on this page
    5. Module 3, episode 21Connect Your AppsGive it the apps the job runs on, with only the access it needs.See it on this page
    6. Module 3, episode 22Its First Job AloneThe same job, now running without you.See it on this page
    7. Module 3, episode 23Keep It RunningMaintenance, security and running cost.See it on this page
    8. Module 3, episode 24Build Your Agent TeamSeveral agents working together.See it on this page
  5. Module 4Choose your projects4 projects

    1. Your projectschoose the ones you want
      • Your projects, a choiceResearch AnalystDelivers a competitive research brief on your market every Monday, without anyone starting it.See it on this page
      • Your projects, a choiceVideo EditorTakes raw footage to a first cut the way you edit, ready for your review.See it on this page
      • Your projects, a choiceContent EngineTurns your notes and recordings into a week of posts for your channels, drafted for your approval.See it on this page
      • Your projects, a choiceOutreach RepFinds the right prospects, writes a personal first message for each, and sends it on your approval.See it on this page
  6. The finish

    1. Module 4, with a mentorA process of your ownPick a process from your business and build the agent for it, with a mentor beside you.See it on this page
    2. The end of the pathYour agents, at workThe agents you chose, running the business processes you picked.

Curriculum

What you learn, module by module.

Modules 1 to 3 take one real job from a plan to an agent that runs it. In Module 4 you choose the agents you build next.

  1. Module 1 · 7 episodes

    Understand AI agents

    How agents, harnesses and models work, and where each fits in a business process.

    What happens in Module 1

    What an AI agent is, the harness that runs around the model, the five layers up to an autonomous agent, local or cloud models, the agent loop, and the AI Implementation Map you plan every build with.

    Episode 01: an agent takes a goal, decides, acts and checks the results, until the job is done or it needs you
    Episode 01What Is an AI Agent?

    You leave this module withA plan for your agent, mapped on the AI Implementation Map.

    1. 00What You'll Build
    2. 01What Is an AI Agent?
    3. 02What Is an AI Harness?
    4. 03The Five Layers of AI Harness
    5. 04AI Models: Local or Cloud?
    6. 05How an Agent Works
    7. 06The AI Implementation Map
    What each episode covers
    What You'll Build
    What you will have built by the end.
    What Is an AI Agent?
    What an agent is, and how it differs from a chat assistant and a workflow.
    What Is an AI Harness?
    The system around a model: goal, context, tools, memory, permissions and a loop.
    The Five Layers of AI Harness
    Five ways AI is put to work, from chat to autonomous agents.
    AI Models: Local or Cloud?
    Where a model runs, and what that means for privacy, cost and capability.
    How an Agent Works
    How an agent works toward a goal: observe, decide, act, repeat.
    The AI Implementation Map
    Five questions to plan a process before you build.
    Episode 06: Luka maps a business process from input to output and finds the step where the work waits
    Episode 06The AI Implementation Map
  2. Module 2 · 10 episodes

    Build a custom AI agent

    Set it up, connect it to your tools, and train it with skills, guardrails and a known cost per task.

    What happens in Module 2

    Set up your first local agent, connect it to your apps and to GitHub, and run your first real job: a client call becomes a project brief and owned tasks on your board. Then turn that procedure into a skill, learn what each run costs and set your guardrails. The module's project is a real one: how Luka edits video with AI, in four parts.

    Episode 07: Claude Code running in a project folder, with auto mode explained on screen
    Episode 07Set Up Your First Local AI Agent

    You leave this module withA custom agent on your machine, trained with a skill, on guardrails, at a known cost per run.

    1. 07Set Up Your First Local AI Agent
    2. 08How Agents Connect
    3. 09Connect Your Agent to GitHub
    4. 10Your First Job
    5. 11What Is a Skill?
    6. 12Turn Your Procedure Into a Skill
    7. 13What It Costs
    8. 14Set Your Guardrails
    9. 15How I Edit Video With AI
    10. 16Becoming Autonomous
    What each episode covers
    Set Up Your First Local AI Agent
    Install an agent, give it a folder and a first task.
    How Agents Connect
    Three ways an agent reaches your apps: an API, MCP and a command line.
    Connect Your Agent to GitHub
    Keep your agent's work in a private repository.
    Your First Job
    A meeting transcript becomes a brief and tasks on your board.
    What Is a Skill?
    Your way of doing a task, written down for an agent.
    Turn Your Procedure Into a Skill
    Save the job you just ran as a skill.
    What It Costs
    What a run costs, and four habits that keep it low.
    Set Your Guardrails
    Eight risks, and the guardrail for each.
    How I Edit Video With AI
    Luka's editing skill, run on a raw clip and improved.
    Becoming Autonomous
    What an agent needs before it can run on its own.
    Episode 15: Luka's video editing skill, a text file of his own process that the agent gets
    Episode 15How I Edit Video With AI

    Module 2 projects: you build both

      1. Client call
      2. Agent plans
      3. Your board
      Client Delivery, your first jobTurns a client call into a project brief and owned tasks on your board.
      1. Raw footage
      2. Agent cuts
      3. Your review
      4. It ships

      Until you approve

      Your video editing skillLuka's editing skill, run on a raw clip, improved, then used in DaVinci Resolve.
  3. Module 3 · 8 episodes

    Set up an autonomous AI agent

    An always-on agent, connected to your apps, that takes jobs on its own.

    What happens in Module 3

    What an autonomous agent is and how it works. Then set up your first one, add guardrails and a kill switch, connect your apps, and let it take its first job alone. Keep it running, and build your agent team.

    Episode 00: your agent, trained on your process, running on your machines, on your rules, inside your guardrails
    Episode 00What You'll Build

    You leave this module withAn always-on agent on its own machine, on guardrails with a kill switch, connected to your apps.

    1. 17What Is an Autonomous Agent?
    2. 18How an Autonomous Agent Works
    3. 19Set Up Your First Autonomous Agent
    4. 20Add Guardrails and a Kill Switch
    5. 21Connect Your Apps
    6. 22Its First Job Alone
    7. 23Keep It Running
    8. 24Build Your Agent Team
    What each episode covers
    What Is an Autonomous Agent?
    An agent that takes the work, does it your way and reports back.
    How an Autonomous Agent Works
    Its parts, from the model to its permissions.
    Set Up Your First Autonomous Agent
    Set one up on a spare computer or in a sandbox.
    Add Guardrails and a Kill Switch
    What it may do alone, when it asks, and how you stop it.
    Connect Your Apps
    Give it the apps the job runs on, with only the access it needs.
    Its First Job Alone
    The same job, now running without you.
    Keep It Running
    Maintenance, security and running cost.
    Build Your Agent Team
    Several agents working together.
    Episode 17: Luka introduces the course's own autonomous agent, OpenClaw, set up and trained by you
    Episode 17What Is an Autonomous Agent?
  4. Module 4

    Choose your projects

    Pick the projects that fit your business, or bring a process of your own.

    What happens in Module 4

    Choose what you build next. Each project is a custom agent for a real business process; build one, several, or bring a process of your own.

    You leave this module withThe agents you chose, running the business processes you picked.

    Your agents: choose one or more

      1. Every Monday
      2. Agent researches
      3. The brief

      Again next week

      Research AnalystDelivers a competitive research brief on your market every Monday, without anyone starting it.
      1. Raw footage
      2. Agent cuts
      3. Your review
      4. It ships

      Until you approve

      Video EditorTakes raw footage to a first cut the way you edit, ready for your review.
        • Your notes
        • Your recordings
      1. Agent drafts
      2. You approve
      Content EngineTurns your notes and recordings into a week of posts for your channels, drafted for your approval.
      1. Prospects
      2. Agent writes
      3. You approve
      4. Sent
      Outreach RepFinds the right prospects, writes a personal first message for each, and sends it on your approval.

Program guide

Read the whole course first.

  • The cover of the Autonomous AI Automation program guide

    Autonomous AI Automation

    Autonomous AI Automation guide

    The whole course, module by module, in one PDF.

    18 pages, PDF

    We email you the guide, and course news after. Stop any time.

What you get

What you get with the course.

  • The course

    Concrete knowledge of building, training and running custom AI agents.

    28 episodes in 4 modules, taught on camera.

    What you walk away with

    • Custom AI agents, connected to your tools
    • Trained with skills on your procedures
    • Guardrails, permissions and cost control
    • Projects you choose for your business
  • The journey

    From zero to custom AI agents that run your business.

    1. 0Today
    2. Plan it
    3. Build it
    4. Make it run
    5. Put it to work

    Agents you can build

    • Research Analyst
    • Video Editor
    • Content Engine
    • Outreach Rep
  • 0 lines of code you write

    Every step is shown on screen. Module 1 is open now, and a new module opens each week.

  • The AI Automation platform: the course modules, the community feed and upcoming live sessionsAn automation workflow open in the platform's mobile app

    Support on the platform

    Questions, support and discussions are on the AI Automation platform, where the course is, on your computer and in its mobile app.

  • Lifetime access to the program

    Every episode, resource and update stays yours after your last payment.

  • The AI Implementation Map

    The plan you make before every build.

  • The cover of the Autonomous AI Automation program guide

    The program guide

    The whole course, module by module, in one PDF.

Luka Madzarac opening Episode 01, What Is an AI Agent?Luka MadzaracClaude Certified AI System Architect

Your instructor

Taught by Luka Madzarac.

Luka teaches the course on camera. He spent a decade producing brand film, motion design and web, then built the agent system his own studio runs on. The course builds that kind of system with you: custom agents, trained to be reliable and run real work.

  • Runs his own studio on AI agents
  • Claude Certified AI System Architect
  • Shows every step on screen

Your mentors

Meet your mentors.

Anthony and Luka mentor both courses. Mentorship is by application.

Anthony Lee, program mentorMentor

Anthony Lee

AI SEO researcher, tool builder, agency partner

From Amazon algorithm work to AI search and the tooling around it. He runs the build-along sessions and mentors the final project, from the idea to something that runs.

TeachesAI Automation

Luka Madzarac, Claude Certified AI System ArchitectMentor

Luka Madzarac

Claude Certified AI System Architect

A decade in brand film, motion design and web, then he built the agent system his own studio runs on. He mentors the creative side: production, web builds, and the agents behind them.

TeachesAutonomous AI Automation

Student stories

What AI Automation students say.

Read our reviews on Trustpilot (opens in a new tab)
  • It's one of the most beautiful courses I've ever experienced. The graphics The animation The resources

    Dave KatagueMultidisciplinary Creative & AI Strategist · AI Automation student

    Dave Katague on LinkedIn (opens in a new tab)
  • Value-packed course and next-level community. Luka and Anthony go above and beyond, constantly sharing real-time tips, insights, and blueprints that are immediately useful. I'm genuinely grateful to have been part of this experience. Wishing the whole team continued success!

    Rio GonzalesHead of Operations · AI Automation student

  • Very good program. Totally worth it the investment. It requires a lot of focus and dedication but the outcomes are very good!

    Giuseppe MiloProduct & Growth Manager · AI Automation student

    Giuseppe Milo on LinkedIn (opens in a new tab)

More

More about the course.

With a custom agent

The work runs. You check the results.

With a custom agent

The work runs. You check the results.

One example day: jobs that start on a schedule, on an event and overnight.

Module 4: choose your projects

Pick what you build.

Module 4: choose your projects

Pick what you build.

Build one of these agents, several, or bring a process of your own.

  • Choice 1

    Research Analyst

    Delivers a competitive research brief on your market every Monday, without anyone starting it.

    RunsEvery Monday morning

    Working

    MakesThe research brief

    1. Starts on its ownDone
    2. Reads the sources you setDone
    3. Writes the research briefWorking
    4. The brief, ready for youNext

    GuardrailWorks only from the sources you set

  • Choice 2

    Video Editor

    Takes raw footage to a first cut the way you edit, ready for your review.

    RunsWhen new footage lands

    Waiting for you

    MakesA first cut

    1. Picks up the new footageDone
    2. Cuts it the way you editDone
    3. Waits for your reviewNeeds you
    4. It shipsNext

    GuardrailYou review every cut before it ships

  • Choice 3

    Content Engine

    Turns your notes and recordings into a week of posts for your channels, drafted for your approval.

    RunsEvery week

    Working

    MakesA week of posts

    1. Reads your notes and recordingsDone
    2. Drafts a week of postsWorking
    3. You Approve the draftsNext
    4. Posts to your channelsNext

    GuardrailNothing posts until you approve it

  • Choice 4

    Outreach Rep

    Finds the right prospects, writes a personal first message for each, and sends it on your approval.

    RunsEvery weekday

    Waiting for you

    MakesA message for each prospect

    1. Finds the right prospectsDone
    2. Writes a message for eachDone
    3. Waits for your approvalNeeds you
    4. Sends themNext

    GuardrailNothing sends until you approve it

Or

Your own processWith a mentor

Build your own agent

Pick a process from your business and build the agent for it, with a mentor beside you from the plan to the guardrails.

Apply for mentorshipBy application. A short form, then a call.

StartsWith four questions

Yours to build

  1. How does the process start?
  2. What information does it need?
  3. What is the final outcome?
  4. Which decisions stay with you?
What you build

Custom AI agents you can rely on.

What you build

Custom AI agents you can rely on.

  • Custom AI agentsBuilt for one business process and connected to the tools it runs on.
  • Trained with skillsYour procedures, written once and executed the same way every time.
  • Run on guardrailsPermissions, checks and a known cost per task, so it works securely.
  • Running on their ownOn schedules, on events and always on, with you approving what matters.
What a trained agent does

Five steps of the process, handed to your agent.

What a trained agent does

Five steps of the process, handed to your agent.

A custom agent runs a business process end to end, inside the guardrails you set.

  • 01

    Picks up the work

    It starts on a schedule or an event, without anyone asking.

  • 02

    Follows your procedure

    Trained with skills, it does the job your way, every time.

  • 03

    Moves the information

    Connected to your tools, it reads the inputs and writes the results.

  • 04

    Checks the result

    Guardrails and checks run before anything leaves the process.

  • 05

    Brings you the decisions

    It stops at the points you choose and asks you to approve.

How an agent works

The loop that does the work.

How an agent works

The loop that does the work.

An agent takes a goal, decides, acts, checks, and repeats until the job is done or it needs a person.

01Observe. Decide. Act.The whole cycle is the agent loop, continuing toward the goal one turn at a time.
02The model decides. The harness acts.Context goes to the model, instructions come back, and the harness runs the tool.
03Every turn is a new request.The loop continues with the results of the last action, until the job is done.

In the course's own words, from Episode 05, How an Agent Works.

Who it is for

Built for business processes.

Who it is for

Built for business processes.

  • You run processes that repeat

    Reports, follow-ups, client work: the jobs a custom agent executes.

  • You want systems, not prompts

    Agents with skills, guardrails and known costs, built to be relied on.

  • You want what lasts

    Platform agnostic: the principles hold as models and tools change.

Where it sits

From workflows to agents that work on their own.

Where it sits

From workflows to agents that work on their own.

AI Automation teaches level one, workflows that run a process. This course takes you through the next two.

  1. Level 2

    AI agents

    An agent with your tools and procedures, taking on a real job.

    Autonomous AI AutomationThis course

  2. Level 3

    Autonomous AI agents

    Agents that run on their own while you check the results.

    Autonomous AI AutomationThis course

Plans

Choose your plan.

Start with one course, get both with Pro, or build your own project with a mentor.

One course

Autonomous AI Automation

$79/month for 12 months

Then lifetime access to the course. Or pay $799 once and save $149.

60 spots left at this price

Until 31 December, every new student gets a 30-minute setup call with Luka.

Learn to build, train and run custom AI agents.

  • Custom AI agents, connected to your tools
  • Trained with skills on your procedures
  • Guardrails, permissions and cost control
  • Projects you choose for your business
Start from $79

7-day refund policy.

RecommendedBoth courses

AI Automation Pro

$99/month for 12 months

Then lifetime access to both courses.

Or pay once: was $999, now $749

9 spots left at this price

Both courses: AI workflows first, then AI agents.

  • Everything in AI Automation
  • Autonomous AI course
  • Every future course we release
  • Agent skills and project files to download
  • Pro-only workshops
  • Priority help when you get stuck
Get AI Automation Pro

7-day refund policy.

With a mentor

Mentorship

By application

A guided 3-week program, 1 on 1.

  • Everything in AI Automation Pro
  • A mentor on your project, with feedback at every stage
  • Build your own AI automation, from your own idea
  • Lifetime access to the blueprints, resources and network
Apply for mentorship

A short form, then a call.

FAQ

Questions before you start.

$79/month for 12 months, or $799 once

Start from $79
Get AI Automation Pro

Both courses in one plan. From $99/month.

  • 7-day refund policy.
  • Lifetime access
Do I need to code?

No. Every step is shown on screen, and terminals, agents and skills come up only after you have seen what each one is for.

Is the whole course open today?

Module 1 is open now, and a new module opens each week. Each one unlocks when you finish the one before. Take it on its own, with the first course in AI Automation Pro, or with mentorship.

What else do I pay for?

A paid Claude plan. Claude Pro, from $20 a month, covers what you build in the course; the free plan does not. Module 2 shows what each run costs, and four habits that keep it low.

Which tools and platforms do you teach?

Platform agnostic. Models and tools change every few months; how an agent works, how to give it skills, guardrails and a schedule, and how to run it reliably do not. You learn the parts that last, shown today on Claude Code.

Can I choose what I build?

Yes. Modules 1 to 3 build the skills on one real job. In Module 4 you choose your projects: a Research Analyst, a Video Editor, a Content Engine, an Outreach Rep, or a process from your own business. New projects are added each month.

How is it different from AI Automation?

AI Automation teaches you to build AI workflows for business processes on no-code tools. Autonomous AI Automation teaches you to build custom AI agents, train them to execute reliably and cost-effectively, and run them on their own.

Can I get a refund?

Yes, within 7 days of purchase, provided you have not downloaded any course assets: blueprints, documents, videos or other resources.

Terms of Service

Autonomous AI Automation

Build agents that run your business processes.

Custom AI agents, trained on your procedures and run on guardrails.

  • Custom AI agents, connected to your tools
  • Trained with skills on your procedures
  • Guardrails, permissions and cost control
  • Projects you choose for your business

Autonomous AI Automation

$79/month for 12 months

Then lifetime access to the course. Or pay $799 once and save $149.

60 spots left at this price

Start from $79
Get AI Automation Pro

Both courses in one plan. From $99/month.

7-day refund policy.

Want to read first? Get the program guide by email.

We email you the guide, and course news after. Stop any time.

What lifetime access covers

  • All resources and program assetsEvery episode and project in the course.
  • Updates to the courseWhat we add to it or improve in it is yours too.
  • Support on the platformAsk your questions where the course and the community are, for as long as we offer them.
Autonomous AI AutomationFrom $79/mo
See plans