HOSTED BY STEFAN WOLPERS

• Creator of the AI4Agile and Advanced PBM Course w/ 1,000+ Students

• Professional Scrum Trainer at Scrum.org

• Author of Scrum Anti-Patterns Guide

• 40,000+ agile practitioners have trusted my insights for 10-plus years.

​

The form to join the waitlist is at the bottom… 👇

​

A Self-Paced Course for Professionals Who Want More from AI

You have been prompting AI for months. You get decent results on good days and generic filler on bad ones. Every conversation starts from zero because the model forgets who you are, what you do, and what good output looks like for your specific work.

That is the ceiling of prompting. The Claude Cowork Course shows you what is above it.

Claude Cowork is Anthropic's desktop agent. It reads your files, connects to your tools, and runs multi-step tasks on its own. Impressive when it works. Mediocre when it does not know who you are. The difference is not the tool. The difference is whether you have taught the model how you work: your standards, your anti-patterns, your judgment calls. That teaching happens through Skills.

A Skill is a reusable instruction set that encodes your expertise. A prompt disappears after one use. A Skill persists across every future session. Prompts do not compound. Skills do.

The Claude Cowork Online Course teaches you a scalable system to build Skills, connect them to your tools, and assemble AI Agents who handle recurring work the way you would handle it yourself. There is no coding involved.

The Claude Cowork Online Course is in English. 🇬🇧

What You Will Learn to Master

1. Build Skills that encode your expertise. Move from one-off prompts to persistent instruction sets, embedded in a scalable, compounding system. Each Skill captures how you work: your standards, your failure modes, your judgment calls. As a collective, they allow you to delegate work to Agents.
2. Configure your environment so the model recognizes you. The instruction stack (Global Instructions, folder-level CLAUDE.md, User Preferences) is the highest-leverage setup activity. A vanilla Cowork installation guesses. A systematic one knows your role, your standards, and your constraints.
3. Decide what to delegate and what to keep. The A3 Framework (Assist, Automate, Avoid) gives you a decision model for every task. "Can AI do this?" is the wrong question. "Should AI do this, and at what level of autonomy?" is the right one.
4. Connect Skills to external tools and turn them into Agents. A Skill tells the model how to work. A connector gives it access to Google Drive, Slack, Notion, Jira, or 40-plus other services. Combine the two, add a folder structure, and you have an Agent who handles a category of work autonomously.
5. Iterate instead of perfecting. Every Skill is version 1. The course teaches you how to test, break, and improve your Skills, and how to recognize when the next iteration is no longer worth the effort.

Claude Cowork Course Topics

The course follows the same arc that a founding cohort tested in the live Cowork BootCamp (April 2026): experience first, then configure, then build:

1️⃣ Foundation: How Claude Cowork differs from Chat and Code. The Commander's Intent delegation model: define the outcome and constraints, let the model choose the approach. The three-layer instruction stack. Cross-session memory using the memory.md pattern. Token economics on the Pro plan ($20/month). Model selection: when Sonnet is enough, when Opus is worth the tokens.

2️⃣ Skill Creation: The prompt-first method: prompt yourself to a successful output in Chat (cheaper), then package it as a Skill. Skill anatomy (YAML frontmatter, description as trigger, instruction body). Writing anti-patterns into Skills to help the model avoid your known failure modes. The compare-and-contrast quality gate: run the same task with and without the Skill, and measure what gets lost.

3️⃣ Delegation and Judgment: The A3 Framework: Assist (AI drafts, you decide), Automate (AI executes on rules, you audit), Avoid (stays human because failure damages trust). Three failure modes to watch for: rationalizing "Avoid" work, set-and-forget "Automate", rubber-stamping "Assist." The Handoff Canvas: six questions to document decisions for every recurring AI workflow.

4️⃣ Integration: Connectors: giving Cowork access to Google Drive, Slack, Gmail, Notion, Jira, and more. Tool permissions: Allow, Ask, Block. Folder structure: the Goldilocks principle (enough context for the model, not so much that it drowns in noise). Assembling an AI Agent from Skill + connector + folder.

5️⃣ Expanding Reach: Browser integration via Claude in Chrome. Scheduled tasks for recurring automation. Plugins and the Skill ecosystem. Security awareness: prompt injection, folder access boundaries, trust decisions.

6️⃣ Iteration: The inspect-and-adapt loop for your entire setup. When to stop automating: the law of diminishing returns. The 85% principle: the result may be 85% of what you would produce manually. The time savings justify the tradeoff for most tasks. When the gap between 85% and 100% matters, close it by hand.

What Makes This Course Different

1️⃣ You build, you do not watch. Every module produces a working artifact: a configured environment, a Skill, or an Agent. Theory serves construction.

2️⃣ Designed for the $20/month Pro plan. Every exercise works within the Pro plan budget. The prompt-first method front-loads work in Chat (cheaper) and uses Cowork only for packaging and testing.

3️⃣ No coding required. Skills are Markdown files. If you can write a structured document, you can handle Skills. The course is built for knowledge workers: product managers, business analysts, agile practitioners, consultants, coaches, writers, and anyone whose work involves recurring judgment tasks.

4️⃣ Tested with a live cohort. The course content comes from the Cowork BootCamp (April 2026), where real participants built real Skills and told me what worked and what did not.

What You’ll Get

✅ 8+ hours of self-paced video modules covering every concept and exercise, with downloadable materials

✅ The A3 Framework Decision Tree and Handoff Canvas as working handouts you can use on day one

✅ Exercise materials with sample inputs and explicit success criteria for every module

✅ Starter kit: a pre-configured folder structure, example CLAUDE.md, example memory.md, and a working Skill template

✅ The Quick Reference Card for Claude Cowork (setup, delegation framework, model selection, limitations)

✅ Lifetime access to the version you purchase: all texts, slides, prompts, graphics; you name it.

✅ Claude Cowork Foundational Certificate upon completion.

Frequently Asked Questions

• Do I need coding experience? No. Skills are Markdown instruction files. If you can write a clear email, you can deal with a Skill. The course does not use Claude Code or any developer-facing tools.
• What Claude plan do I need? A paid Claude plan. Pro ($20/month) is the minimum. The course is designed for Pro. Max ($100/month or $200/month) gives more room for experimentation.
• Does this work on Windows? Claude Cowork runs on macOS and Windows (x64). Arm64 Windows is not supported yet.
• What AI tools do I need besides Claude? None. The course uses Claude Cowork exclusively. The delegation frameworks (A3, Commander's Intent) are tool-agnostic, but the hands-on exercises require the Claude Desktop app with the Cowork tab.
• How is this different from an AI prompting course? Prompting courses teach you to write better individual inputs. This course teaches you to build persistent instruction sets (Skills) that encode your expertise across every future session within a system. Prompts disappear after one use. Skills compound.
• How much time do I need? Plan for 10-15 hours for all modules, including exercises, depending on your experience. The prompt-first method means you start building in normal Claude Chat conversations before you touch Cowork, so there is no steep on-ramp.
• I already took the AI4Agile Online Course. Is this redundant? No. AI4Agile teaches agile practitioners to use AI in their specific workflows. This course teaches any knowledge worker to restructure how they work with AI through Skills, delegation frameworks, and agent assembly. AI4Agile students will recognize some foundational concepts, but the scope and depth are different. AI4Agile students: check your email for your discount code.
• What if Anthropic changes Cowork significantly? Anthropic rapidly enhances Cowork. Consequently, the interface will change; however, the core methods this course teaches will not: identify recurring work patterns, encode your expertise as reusable instructions, decide what to delegate and what to keep, and iterate based on results. These transfer to any agentic AI tool. The specific Cowork mechanics (folder setup, connectors, Skill installation) may shift in detail. When changes are significant enough to warrant a new course version, I will offer existing students a discounted upgrade.
• What is the refund policy? You get a full refund within 14 days of purchase. No questions, no hoops.
• Will the content stay current as Cowork evolves? The course covers stable patterns (Skills, instruction stacks, delegation models) that persist across interface changes. You keep lifetime access to the version you purchased. When Cowork changes enough to warrant a new course version, I will release it as an upgrade with a discount for existing students.

The Claude Cowork Course Is Available from June 1-8 for $129 — 

After that, $199

Do you have more questions? I am happy to answer them!

Hit me up: stefan.wolpers@berlin-product-people.com.