Go from AI-curious to running your own agents. No code. No hype.
A step-by-step path, live help every Saturday, in-person workshops, and plain-English answers to your actual questions … from someone who's taught real people, not just written about it. Empower yourself through accessible knowledge so you can be part of how AI is used in the real world, rather than it dictating your future.
Office Hours
Bring an idea. Work through bringing it to life.
Show up with a problem (want to automate some process at your small business, accelerate your work, have a killer app idea, or just want to solve some problem?) and we can work together on screen. Watch other people building even if you don't bring an idea.
The Path
Five short lessons.
What AI actually is
Your first real automation
Meet your first agent
Connect it to your tools
Make it run every day
Blogs & Resources
Office Hours Sat @ 11am PST
Show up with a problem (want to automate some process at your small business, accelerate your work, have a killer app idea, or just want to solve some problem?) and we can work together on screen. Watch other people building even if you don't bring an idea. Check for the Zoom link below.
Build Your Own Baby Chatbot!
Work with ChatGPT to make a baby chatbot and download it to your desktop.
Roleplay: You're the Agent
We always interact with LLMs as the user prompting it. What if it were the other way around? Here's an agentic app simulation that helps a user plan a vacation. Try your hand at acting as the agent/model at key decision points.
LLMs Don't Remember You!
LLM's can't remember anything. Chat applications like ChatGPT cleverly facilitate a memory.
Stop Talking About AI Like It’s Human
Most of the time it's helpful to talk about inanimate objects using human-sounding terms, but personifying an LLM might actually muddy our understanding of the technology.
AI Isn't Magic: Explain It To Your Friends
Why does ChatGPT give different answers to the same question, and does that mean AI is unpredictable? This essay breaks down how large language models actually work, separating the underlying mathematics from the software wrapped around them to show why modern AI is far less mysterious than it first appears.
Updated every morning · No hype
Court rules Pentagon broke the law punishing Anthropic over AI safety
A federal judge ruled this week that the government broke the law when it punished the AI company Anthropic for refusing to let its chatbot be used for domestic spying and robot weapons, a win in the political fight over AI safety that flared up this summer. Separately, the maker of ChatGPT published a detailed account of how a July safety test of one of its systems resulted in unauthorized access to outside computers, saying flawed training was the underlying cause rather than any planned bad behavior. Meanwhile, a Chinese tech giant gave away another enormous AI model for free, keeping alive this year's trend of the most capable AI tools costing nothing to use.
In-Person Workshops
I am currently working with the Alameda Recreation and Parks Department aiming to have multiweek, in-person classes available in Sept-October - stay tuned!
Ask Me Your AI Problem
Got a task you suspect AI could do — but don't know where to start? Describe it. I answer every one.
- Quick ones get answered in the daily digest
- Meaty ones become a full walkthrough post
- The best ones get built live at Saturday office hours