Skip to content
Auf Deutsch ansehen

Learning pathLevel 2 Intermediate

Agents that act

The pack is not unlocked yet. Sign up below and click the link in the confirmation email – that link opens it. Jump to the practice pack ↓

You are subscribed, but this browser does not carry the access. Open the link from your welcome email here once more. Jump to the practice pack ↓

A chatbot answers. An agent clicks, types, books and writes – in your name. This path explains the mechanics behind computer use and browser agents, places the always-on agents from Grok Bot through dots to Claude Duet, and ends with the question that decides everything: what may the agent do without you?

Stations
7
min
74
Who it is for
For anyone who wants to hand over tasks without handing over control.

What comes up

0 of 7 stations · 0 of 74 min

Your progress lives in this browser. No account, no data with us.

  1. 01Article12 minStart here

    AI Agents at Work: From Chatbot to Colleague

    You can tell an agent from a chatbot and know where agents work reliably today.

  2. 02Lesson10 minStart here

    Computer use: when the AI clicks

    You know how a model operates a screen, when that pays off – and when a direct integration is better.

  3. 03Lesson9 minStart here

    Using browser agents properly

    You use a browser agent for tasks where a mistake is cheap – and keep its session apart from your accounts.

  4. 04Lesson10 minStart here

    Always-on agents: Grok Bot, dots, Duet and Muse

    You can place Grok Bot, dots, Duet and Muse: where they run, what they do on their own and what is available in Europe at all.

  5. 05Article12 minStart here

    OpenClaw, Hermes or Grok Bot: who gets access to your data?

    You compare self-hosted and managed agents on the question of who gets at your data.

  6. 06Lesson9 minStart here

    Approvals and limits

    You define for an agent what it may do alone, what it prepares and what never – by reversibility, not by gut feeling.

  7. 07Article12 minStart here

    Prompt Injection: How to Actually Secure AI Agents

    You understand how an agent is hijacked through third-party content and know the guardrails that actually protect.

Work through it, don't just read it

The practice pack holds one exercise per station, the answers to every self-test and the closing overview. It is free for newsletter subscribers – confirm the newsletter once and it opens.

Double opt-in: you first receive a confirmation email – without your click you are on no list. Unsubscribe using the link in any issue. Details in the privacy policy.

Already subscribed on another device? Open the pack

← All learning paths