Personal Agents with OpenClaw
Install and configure OpenClaw, connect it to a real chat channel, and learn how to scope trust, tools, and access so your personal AI assistant is genuinely useful without becoming a liability.
Design Safe, Local-First AI Agents
Build a Local-First AI Assistant Without Giving It the Keys to Everything
OpenClaw is a local-first personal AI assistant that runs on your own hardware and connects to chat apps you already use, including Telegram, Slack, Discord, Signal, iMessage, WhatsApp, Teams, Matrix, and WebChat. In this hands-on workshop, you will do more than stand up an agent — you will learn how to decide who can trigger it and what it is allowed to touch before you grant it real power.
We will install OpenClaw, connect a live or simulated chat channel, lock down access with the built-in audit tooling, scope tool permissions, write a custom skill, and finish with a working capstone automation. The emphasis is on judgment as much as mechanics: understanding trust boundaries, applying least privilege, and building a personal assistant that is useful, inspectable, and secure enough to deserve real access.
What You Will Master
- Understand that a personal AI agent is delegated authority, and learn how to deliberately scope both its power and its risk.
- Learn why local-first is not secure by default and how to actually lock down an assistant running on your own hardware.
- Build a clear mental model of OpenClaw’s personal-assistant trust model so you do not mistake it for multi-tenant isolation.
- Apply least privilege across three axes: who can talk to the bot, where it can act, and what it can touch.
-
Read and interpret
openclaw doctor,security audit, andsecurity audit --deepoutput with confidence instead of treating green checkmarks as magic. - Know when to reach for a tool, a skill, or a plugin as you expand your assistant’s capabilities.
- Leave with a reusable security checklist, a custom skill, and a working capstone automation you can keep evolving after the workshop.
Prerequisites
- Basic comfort with the terminal, including running commands, editing config files, and reading command output.
- Some exposure to AI coding tools such as Copilot, Cursor, Claude Code, ChatGPT, or similar tools.
- No prior experience with agent architecture, OpenClaw, self-hosted assistants, or secure automation is required.
- Come with Node.js LTS, npm, Git, and a code editor installed and working on your machine.
- OpenClaw should be pre-installed if possible.
- Bring an API key for at least one model provider with a low spending limit.
- Telegram and Tailscale are helpful but optional; simulated alternatives will be available.
Who is this for?
This workshop is for developers and tinkerers who are curious about personal AI agents and want something they actually control. It is especially well suited for engineers drawn to local-first tools and for anyone considering giving an agent access to messages, files, a browser, or a shell and wanting to do that responsibly. It is not aimed at people looking only for prompt-engineering tips, teams shopping for managed SaaS agents, or anyone who needs airtight multi-tenant isolation without understanding the underlying trust model.
Replay coming soon.
Build a personal AI assistant end to end, then make it trustworthy by deliberately constraining identity, channels, tools, and access.
Install and configure OpenClaw, connect it to a real chat channel, and learn how to scope trust, tools, and access so your personal AI assistant is genuinely useful without becoming a liability.
Warning: High intensity learning environment.
Attend Online Live and in Full HD
The Workshop is Live Now!
Watch the Replay
This Workshop Has Ended
Or Join In-Person from Downtown Minneapolis
Catch up on everything you missed.
A Full Day of Mastery.
Live, interactive workshops typically cost hundreds. Get the full experience at no cost — join a full-day session, ask questions in real time, and learn directly from expert instructors.
Missed the live session? Watch the full recording at your own pace and get the same expert instruction on demand.
Upcoming Live Workshops
Building with AI Bootcamp
Agentic Frontend Development with OpenAI Codex
Local Agentic Coding Setup
Codex for Backend Engineers
Laravel Fundamentals
Professional AI Dev Setup, v2
Build AI Agents that Never Sleep
Building Custom Agents with Claude Code SDK
Practical AI Agent Workflows
Django Fundamentals
Complete Intro to AI
