OpenClaw: From Zero to a Self-Running AI System
Control your computer by voice, then let agents run the work.
A live build-along. Install OpenClaw in Docker, drive it from WhatsApp with a keyword you choose, and connect it to Google Workspace through the gws CLI so it can create and fill real documents. It runs with a self-repair 'doctor' loop, and you give it genuine work: a scheduled job that warns you when disk drops below 10%, a spreadsheet built by voice, an agent that reports on your own commits. It closes on how far the pattern scales — a self-healing VPS, Kubernetes driven by prompt engineering, and a company of agents in production.
$20.00 USD
What you will learn
- Install OpenClaw in Docker and control it from WhatsApp or Telegram with your own keyword
- Drive Google Workspace programmatically with the gws CLI — Sheets, Docs, Drive, Calendar
- Nest the orchestration: OpenClaw drives Claude Code, which dispatches its own agents
- Add a cloned voice so you can approve and trigger work by speaking
- Keep it alive with a self-repair 'doctor' loop, and let a verifier agent check the work
- Hold context in local markdown memory instead of burning tokens on every call
- Scale the pattern to a self-healing VPS, Kubernetes by prompt, and multi-agent teams
What is included
- Full recording of the live session (MP4, download and keep)
- Complete written transcript
- Private download link, delivered automatically after payment
Other masterclasses
MasterclassSecurity: AI Agents That Audit Your Own Stack
MasterclassWhatsApp + AI: Baileys, RAG & Fine-Tuning
Programme1:1 AI Engineering Training
Prefer live, personalised sessions? The 1:1 programme covers all of this and builds your own system over 20 hours.