Skip to content
agenticbuilders
Pass

Text courses · from Vienna

Use Claude Code to build apps that still run after the demo.

I'm Bernhard, a software developer in Vienna, and three of my products are live. My text lessons show you how I work with Claude Code. You can read the first lesson of every course without signing up.

See the All-Access PassRead the first lesson free

Inside the AI Builder Guide you get BuilderBob: a prepared AI co-pilot that interviews you and builds with you. It guides; you click, paste, and verify. That way it stays your app, and you understand what is happening.

View the AI Builder Guide

Never worked with Claude Code? Start with the free Werkbank course

10+ years in IT · 500+ AI prototypes · 1st place BitGN Hackathon

AI builder from Vienna
Bernhard Götzendorfer

Choose your starting point

Where are you right now?

Three ways into the courses, depending on what you already bring.

  • Go deeper with Claude Code

    For people who already use Claude Code.

    You get all 10 paid courses in one purchase, including Claude Code Capabilities and Loop Engineering.

    Level: advanced

    €99

    See the All-Access Pass

  • Your first own app

    For anyone who wants to build their first AI app.

    In the free Werkbank course you set up the terminal, Node and Git. Then you build your first app with the AI Builder Guide.

    Level: beginner, you learn the tools in the course

    free

    Next: AI Builder Guide €29 · View the AI Builder Guide

    Start Werkbank for free

  • No code

    For office work, founders and anyone who does not program.

    You handle files, research and office routines with AI agents, without writing a line of code.

    Level: beginner, no prior knowledge

    from €49

    Go to the no-code course

View all 11 courses

Build in public

What I've built.

All three are publicly available, so you can look at them before you buy anything.

  • 1st place, BitGN Hackathon Vienna. Solo, 3 hours on site
  • 500+ AI prototypes · own agentic tools in daily use

It runs locally. So why does it break live?

You give Claude Code a task, and an hour later the feature runs on your machine. Then it goes live. An edge case fails, a key sits in the repo, and the next refactor breaks something that used to work. Nobody checked it. You didn't either. It ran.

That's not your fault. Claude Code writes code that looks finished, and it writes it fast. It doesn't tell you on its own whether that code holds. Usually three things are missing: tests, a verification step with evidence, and a second pair of eyes before the merge.

You can make those three things a habit. They keep working when the next model ships.

In the courses I show you how I do this in my own products: subagents that review the work, hooks that kick off the tests, and a loop that only moves on once there is evidence.

01Collect context02plan03let AI build04verify05repeat

The method loop

Five stations, one loop: collect context, plan, let the agent build, verify, then run the next round.

Verification is the step most people skip. It is the difference between a demo and an app you can actually judge.

Already know how to code?

Then your gap is the move from works on my machine -> works reliably: verification as a habit, clean secrets, reproducible deploys, and checked GDPR basics. That is exactly what the AI Builder Guide is built for. Go to the AI Builder Guide.

For beginners

Free to start: the Werkbank

The Werkbank course walks you through the terminal, Node, Git and Claude Code, step by step.

I'll send you the free handout (PDF) by email, sign up below.

Claude Code tips by email

As a welcome you get the free handout, then a practical Claude Code tip now and then.

  • Delivered straight to your inbox, with no account and no hoops to jump through.
  • Double opt-in, self-hosted fonts, no Google CDN.
  • No spam, and your email is never shared.
  • One click to unsubscribe, any time.

Straight to your inbox

Enter your email, confirm, done. Add your first name only if you want a more personal note.

Helps me see which channels work. Not required.

More in the privacy policy.

Available now · platform access

The AI Builder Guide: from zero to an app you can trust.

The guide takes you from the first prompt to a simple app you can inspect, understand, and publish. Step by step, with a method behind it, not just a recipe.

  • The method. A complete walkthrough from the first plan to the first version you can verify.
  • 10 use-case cards. Reusable cards for typical ideas that you can adapt to your next project.
  • Reliability depth. Verification, security, costs, deploys, and a GDPR checklist. The part quick demos usually leave out.

Written for both ends: approachable enough for a first start, deep enough that you do not get stuck after the polished demo.

The guide is also part of the All-Access Pass, along with the nine other paid courses. All 11 courses in the catalog

Logged-in platform dashboard with the guide card, progress bar, and a continue button
This is your learning area after purchase: all lessons directly in the browser.

Price

Price: 29 euros

one-time purchase · no subscription · all 23 lessons in the browser right away

Buy guide (€29)

Final price · voluntary 14-day money-back guarantee. One email is enough.

If the depth does not deliver what it promises here, you get your money back, no debate and no explanation required.

Not sure yet? Find the right starting point ↑

Next step

Multi-Agent Orchestration in Practice (€49)

From a single prompt to a coordinated agent pipeline. Available now: buy and start right away.

View course

I do not sell anything here that I do not use every day myself.

I build real products with AI agents: BuchhaltGenie(opens in new tab), WalkAITalkie(opens in new tab) and EventDrop(opens in new tab) are live. Add more than 500 prototypes and my own agentic tools that I use daily. 10+ years in IT, now deeply focused on AI, plus AI literacy under EU AI Act Article 4 (ki-fit.at). Here I show the method behind it in public. Not a marketing promise, but the path I actually use.

A security analysis of quickly built apps shows how large the gap is: many critical vulnerabilities. Source: escape.tech(opens in new tab) . That is why a reusable method matters more than a fast demo.

Frequently asked questions.

Ask questions, show progress, and get honest feedback without marketing noise. The Discord community is the place for that.

Join Discord (opens in new tab)