Agentic AI with Pete
A small-cohort course on agentic AI for knowledge work.
From a calm and compassionate instructor. Get set up, get grounded, get productive.
A small-cohort course on agentic AI for knowledge work.
From a calm and compassionate instructor. Get set up, get grounded, get productive.
Agentic AI is the new approach to working with AI to get things done. Not chatting. Not prompting. Working together — with an AI that can read files, write code, manage projects, and take real action on your computer.
This course gets you started quickly and keeps you grounded. You'll have a full-blown agentic AI set up on your computer after the first session. The rest of the program turns you and your AI into an effective, productive team.
We'll use Claude Code, installed via plugin using Obsidian or VS Code as the file manager. This is easy to use but not a starter kit — it's full-strength, the same tool seasoned professionals use. We'll also look at Codex, Manus, OpenClaw, and other agentic AIs as they fit.
You need to be conversant with using files and folders on your computer. You don't have to be a computer whiz — the AI handles the fancy stuff.
You write, research, manage projects, build documents, or coordinate teams. You've seen AI demos and maybe tried ChatGPT, but you haven't found a way to make AI a real part of how you work. This course bridges that gap.
This isn't a lecture series. Every session involves hands-on work with your own AI on your own computer. You'll build real things — a website, a wiki, a novel outline, a web app — and develop instincts for when AI helps and when it gets in the way.
There are a lot of AI courses selling magic. This one teaches craft. You'll learn what agentic AI actually does, how to direct it, and how to build your own judgment about the tools as they continue to evolve.
Subject to change — AI changes quickly!
We'll install Claude Code on your machine through Obsidian or VS Code and get you working with it before the session ends. Catch-up sessions available if you need extra help.
Version control isn't just for programmers. Learn how to track changes, undo mistakes, and keep a clean history of your work — with your AI doing the heavy lifting.
Your first real project: a simple personal website, built collaboratively with your AI. You'll see how to direct it, review its work, and iterate.
Organize what you're learning into a structured, searchable knowledge base. A practical exercise in directing AI to create and maintain a body of knowledge.
How to break work into pieces your AI can handle, track progress, and manage the collaboration. The meta-skill that makes everything else work better.
An ambitious creative project that shows both the power and the limits. You'll learn how to maintain voice, continuity, and quality across a long-form work.
Applying the wiki concept to a team setting. How to structure shared knowledge so it's useful, current, and maintainable.
Under the hood: how to pick the right model for the job, manage what data goes in and comes out, and tune your setup for your specific needs.
OpenClaw (formerly ClawdBot) is many people's first exposure to agentic AI — it went viral. But it's complex and under-powered for most knowledge work compared to Claude Code. We'll compare them honestly and talk about when each makes sense.
From idea to working application. We'll build something functional and deploy it, showing how agentic AI handles a more complex, multi-step project.
Your AI gets better when you teach it about your work. Learn how to build custom instructions, workflows, and knowledge that make your AI increasingly effective over time.
The meta-session. How to sustain a productive partnership with agentic AI without burning out. You're the bottleneck on judgment and architectural decisions — and that's by design. We'll cover pacing yourself, sleeping on it as a real work activity, high-signal ways to keep up with the state of the art, and knowing when to step away and let your subconscious do the work.
An optional session in week 7. We look back at six weeks of work together, take stock of what stuck, and talk about where to go next.
Most AI courses leave you with concepts. This one leaves you with a working setup, real projects you built, and the skills to keep going on your own. After six weeks, agentic AI will be part of how you work.
Ten seats. One instructor. Personal 15-minute consults whenever you need them. This isn't a webinar with a thousand attendees — it's a working group where you can ask questions, get unstuck, and learn from each other.
AI tools change fast. The specific buttons and commands will evolve. What won't change is your ability to evaluate tools, direct AI work, and know when to use it and when not to. That's what we're building here.
Pete has been working with agentic AI full-time for over a year — building products, developing workflows, and figuring out what actually works. This course condenses that into 12 hours so you can skip the false starts and get productive on a foundation that's already been tested.
Pete has spent 35+ years building things with emerging technology — and then helping other people do the same. He has a pattern: he spots transformative tech early, builds real products with it, and teaches others how to use it well.
He started in the early 1980s writing video games at Activision and Cinemaware. In 1993, he conceived and led development of one of the first GUI internet navigators — years before mainstream web browsers. In 2003, he co-founded Socialtext, one of the first enterprise wiki and collaboration platforms. In 2024, he co-founded YouBots.ai, an AI SaaS platform with multi-agent orchestration. He started using Claude Code the day it launched in February 2025 and has used it daily since as his primary development tool.
In between, he's been a fractional CTO, a consultant on Agile practices for the Cutter Consortium, and the founder of a five-year public-benefit project providing collaboration tools to distributed communities. He's spoken at SXSW, Web 2.0 Conference, and Intel Developer Forum. He studied Computer Science and Literature at Caltech.
Pete is known for bridging technical depth with plain-language clarity — for helping non-technical people do sophisticated things with technology. That's what this course is. He's not here to impress you with jargon. He's here to get you productive.
Not sure if this is right for you? That's fine. Book a free 15-minute call and we'll figure it out together. No obligation, no sales pitch.
Book a Free Consult