AECO, AI, BIM, Code-ish, Coding, Learning, LLM, Vibe Coding

From Chat to VS Code: Somewhere Between Vibe Coding and AI-Assisted Coding

What changes when you take AI out of the chat window and into VS Code?

I recently completed a course from Brad Traversy at Traversy Media called Coding with AI.

I was looking to move beyond chatting with AI for my “vibe coding” sessions and into something a bit more structured. Up to this point, most of what I was building had to fit inside the limits of tools like Claude or ChatGPT in a browser. It worked, but as projects got larger and more complex, the cracks in that workflow started to show, especially if this was going to be more than just a weekend experiment.

I had dabbled with tools like Cursor, Windsurf, and early versions of Claude Code, but quickly realized I wasn’t ready for them yet. Or maybe I just didn’t need that level of horsepower. Or maybe I wasn’t ready to give up that much control. Likely a mix of all three.

That shift, from chatting with AI to working with it inside VS Code, sounds small. And technically, it is. But it changes how you work more than you think. It comes down to the difference between what the course calls “vibe coding” and AI-assisted coding. I’ll get into that distinction in a bit.

This isn’t a course review, but I liked it enough to go through it twice. Once using Claude Code, and again using Codex. Same material, different tools, slightly different experience each time.

And that’s what got me thinking. Where’s the line between vibe coding and AI-assisted coding? More importantly, where do I actually sit on that spectrum, and what do I gain by moving out of the chat window and into VS Code?

This isn’t a course review, but I liked it enough to go through it twice.

Continue reading “From Chat to VS Code: Somewhere Between Vibe Coding and AI-Assisted Coding”
AECO, AI, BIM, Code-ish, Coding, CSS, HTML, JS, openBIM, Vibe Coding

Just the Fields: A Simpler Way to Explore Large (and Messy) JSON Data

Solving the mystery of your JSON, one field at a time. 🕵️.

I have been doing a lot of work with JSON lately, which got me thinking. There has to be a better way to view all this data.

Technically, JSON is human-readable. But once you are dealing with hundreds or thousands of data points from an API response, it quickly stops feeling very human-friendly. Large responses turn into walls of nested objects and arrays, and even with formatting or collapsible trees it can still be difficult to quickly find the pieces of information you actually care about.

JSON is technically human-readable.
Until it is 5,000 lines long.

Continue reading “Just the Fields: A Simpler Way to Explore Large (and Messy) JSON Data”
AECO, AI, API, BIM, C#, Data, Dynamo, Dynamo 3.0, For The Love Of Code, REST API, Vibe Coding

Here Boy! Meet DynaFetch for Dynamo 3.0

Who’s a good boy? DynaFetch always brings back the data you need. 🐕

For about a month leading up to #AU2025, I’ve been “Vide Coding” with my coding “bestie” Claude (from Anthropic) on our very first custom Dynamo package. DynaFetch brings modern, reliable REST API integration to Dynamo 3.0, letting you connect to external data sources with community-driven, open-source functionality.

This project started because I’ve long relied on the excellent custom package DynaWeb by Radu Gidei. Unfortunately, it isn’t compatible with Dynamo 3.0+, and staying on older versions is becoming less and less practical.

Continue reading “Here Boy! Meet DynaFetch for Dynamo 3.0”
AECO, AI, BCF, BIM, buildingSMART, CSS, For The Love Of Code, HTML, JS, openBIM, Vibe Coding

Introducing BCFSleuth

🕵️‍♀️ Sleuthing through your BCF files so you don’t have to.

Built over a long weekend using Vibe Coding and a solid assist from AI, BCFSleuth is a lightweight, browser-based app that lets you explore and export BCF files (2.0, 2.1, 3.0) with zero setup.

🔍 Quickly preview BCF data
📁 Export to clean, structured CSV or Excel
📸 View and export images
🛡️ No servers — runs entirely client-side
📱 Mobile-friendly for on-the-go use

Continue reading “Introducing BCFSleuth”
AI, Code-ish, Coding, CSS, For The Love Of Code, Hackathon, HTML, JavaScript, Low-Code, No-Code, Vibe Coding

Building🏌️‍♂️Par-Tracker 42 🤖: Why “For the Love of Code” Perfectly Captures the Spirit of Joyful Development

AI image created with NightCafe: For the Love of Code. And if it’s an AI-assisted hackathon for GitHub, even better!

When GitHub announced their For the Love of Code summer hackathon, I knew exactly what they meant. Sometimes the best projects aren’t born from business requirements or feature requests, they come from that spark of “wouldn’t it be cool if…” that every developer knows.

The Ultimate Answer to Golf Score Tracking Needs

Today, I had one of those perfect coding sessions that reminded me why I fell in love with development in the first place. Working alongside Claude Sonnet 4 AI, I built and fine-tuned 🏌️‍♂️Par-Tracker 42 🤖, a web-based golf handicap calculator that embodies everything the “For the Love of Code” hackathon celebrates.

Continue reading “Building🏌️‍♂️Par-Tracker 42 🤖: Why “For the Love of Code” Perfectly Captures the Spirit of Joyful Development”