Wan Wei, Soh "begged" me to teach this course.
Today, I am launching Foundations of Claude Code, a 4-hour course on May 7, for non-techies who want to learn Claude Code properly and walk out with their ow...
Today, I am launching Foundations of Claude Code, a 4-hour course on May 7, for non-techies who want to learn Claude Code properly and walk out with their own website live on a real URL.
What you learn is not Claude Code specific. The same foundation transfers to any AI agent tool you pick up next: OpenClaw, Codex, and whatever comes after. It also transfers beyond coding: drafting, research, automation, analysis, almost anything you want AI to do for you. Claude Code and the website are just the practice tool and project. The mental model and transferable knowledge are the real takeaways.
A few friends have been asking me to teach this for a while. I held back because I wasn’t sure if there would be enough demand to form a minimum class size, considering the market already has many AI courses.
What changed my mind: I have seen many non-techies start to use Claude Code and play with OpenClaw without understanding the foundations of AI agents.
Beginners pushing API keys to public GitHub repos without knowing. Vibe coders telling Claude Code “do not delete my database”, then watching it delete the database anyway. AI breaking the code with no way to undo, because nobody told them to use version control from day one. The traps in the foundation are countless. Most of them are quiet. They bite you weeks later.
The foundation matters more than people realise. Get it right and you stop walking into the traps. Get it wrong and you spend six months debugging things you should never have touched.
What is in the workshop:
-
Foundation in plain English. No jargon. No assumptions about what you know. A working mental model for Claude Code and any AI agent you touch after.
-
Apply and integrate immediately. You build a personal brand or company website in the room. By 5:30pm you have a live URL on free Cloudflare or Vercel hosting.
-
The foundational concept. CLAUDE.md / AGENTS.md, agent skills, subagents, MCP, environment isolation, version control, deployment, the things that take most people months to figure out, distilled into one afternoon.
-
Hands-on, expert guided. My knowledge from 19 years of building products and websites, handed to you while you are actually using them, so you walk out able to keep going on your own.
-
A post-workshop support group, so you are not stuck alone with version two.
Best for: non-technical founders, freelancers, consultants, professionals who want their own digital profile and the foundations of AI for everything else after.
Not for: developers and engineers looking for an advanced deep-dive.
Details:
Date: May 7, 2026, 1:30pm to 5:30pm
Location: Hashmeta Group, 30A Kallang Place, Singapore 339213
Price: S$268 per seat
Page: https://lnkd.in/e9r8kScw
If Wan Wei convinced you to sign up, tag her in the comments.
#ClaudeCode #AI #AIAgents
Enjoyed this? Subscribe for more.
Practical insights on AI, growth, and independent learning. No spam.
More in Vibe Coding
Has Cursor Gotten Worse Over the Last 4 Months?
When I first started using Cursor, I was blown away. With a single prompt, it generated clean, multi-file codes that mirrored exactly how I would have writte...
I caught Cursor trying to be lazy.
The AI agent couldn’t solve the typing error, so it cast the variable to 'any' to suppress the error, just like a sloppy software engineer would.
Gemini CLI stubbornly insisted its code was right and even did a Google search to prove it with an outdated article.
I was speechless. 😂
Claude Code vs Codex vs Gemini CLI vs Qwen: My Results
The winner is still Claude Code...
We tested ChatGPT 5’s front-end coding capability so you don’t have to.
The verdict? Not impressed.
Am I the only one feeling uneasy building AI agents with OpenCrawl after testing it for a while?
I've been building AI agents before OpenClaw, and building skills using Claude Code for a while. It's powerful. When I learned about OpenClaw, I knew exactly...
Has Cursor Gotten Worse Over the Last 4 Months?
When I first started using Cursor, I was blown away. With a single prompt, it generated clean, multi-file codes that mirrored exactly how I would have writte...
Gemini CLI stubbornly insisted its code was right and even did a Google search to prove it with an outdated article.
I was speechless. 😂
We tested ChatGPT 5’s front-end coding capability so you don’t have to.
The verdict? Not impressed.
I caught Cursor trying to be lazy.
The AI agent couldn’t solve the typing error, so it cast the variable to 'any' to suppress the error, just like a sloppy software engineer would.
Claude Code vs Codex vs Gemini CLI vs Qwen: My Results
The winner is still Claude Code...
Am I the only one feeling uneasy building AI agents with OpenCrawl after testing it for a while?
I've been building AI agents before OpenClaw, and building skills using Claude Code for a while. It's powerful. When I learned about OpenClaw, I knew exactly...