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

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

The BIMsider
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

The BIMsider
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, BIM, Code-ish, Coding, Data, Dynamo, LLM, VDC, Vibe Coding

Vibe Coding: The Reality

The BIMsider
Vibe Coding, the “Reality” – Image by ChatGPT

Somewhere between hype and habit

Remember when vibe coding felt like magic? The thrill of fast wins, the rush of ideas turning into working code before your coffee got cold. Then came the hangover, the bugs, the rewrites, the weird “why did it do that?” moments that made you question everything.

Welcome to The Reality.

Vibe coding isn’t about chasing magic. It’s about trusting the tool and mastering the craft.

This is where the dust settles. Where the hype cools down and what’s left is what actually works. Vibe coding isn’t a revolution anymore, it’s just part of the workflow. A tool that sits beside your IDE (that’s VS Code for me), your notebook, and your morning playlist. Not perfect, not broken, just… normal.

It’s not about what vibe coding was, it’s about what it is.

Continue reading “Vibe Coding: The Reality” →
AECO, AI, BIM, Code-ish, Coding, Data, Dynamo, LLM, VDC, Vibe Coding

Vibe Coding: The Bad

The BIMsider
Vibe Coding, the “Bad” – Image by ChatGPT

When the Vibes Wear Off

Remember the end of The Good? That pure buzz when code just vibes, ideas flying faster than your fingers while your AI buddy cheers you on. But then something changes. It gives you, “You’re right, this is wrong, let me fix it,” and you get the same wrong code again. And again. And again. Suddenly the magic fizzles. The vibe stops vibing.

That’s where this part of the story begins.

Starting a build with vibe coding feels effortless. Finishing it depends on how much frustration you’re willing to outlast.

This is Part Two of Vibe Coding: The Good, The Bad, and The Reality, the moment we trade in our white hats for black ones and talk about what happens when the glow fades.

Continue reading “Vibe Coding: The Bad” →
AECO, AI, BIM, Code-ish, Coding, Data, Dynamo, LLM, VDC, Vibe Coding

Vibe Coding: The Good

The BIMsider
Vibe Coding, the “Good” – Image by ChatGPT

The rush of getting code to vibe

Remember your first hackathon? That wild, caffeine-fueled moment when code actually worked on the first try? Even if you’ve never been to one, you know the feeling when everything just clicks and ideas start to flow faster than you can type. Vibe coding feels like that, only this time it happens on an ordinary Tuesday afternoon with no sleep deprivation required.

This post is part one of the three-part series “Vibe Coding: The Good, The Bad, and The Reality.” In this first chapter, we explore the excitement, creativity, and early wins that make vibe coding feel almost magical.

Vibe coding isn’t about knowing everything. Nope! It’s about staying with it long enough to build something real.

Vibe coding lives somewhere between creative flow and AI-assisted development. It is the new rhythm of building software fast, playfully, and with fewer blockers. It’s not about understanding every line behind the curtain, and there’s no need for perfect syntax or detailed documentation. It’s about energy. You are riffing with an AI coding BFF, chasing the spark that turns ideas into working prototypes before your focus fades.

It is coding with momentum.

Continue reading “Vibe Coding: The Good” →
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

The BIMsider
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

The BIMsider
🕵️‍♀️ 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

The BIMsider
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” →
AEC, AECO, AECTechCon, AI, API, BIM, Coding, Learning, Low-Code, No-Code, VDC, Vibe Coding

#AECTechCon, Low-Code & AI, Oh My!

The BIMsider
Image created with Reve.art

Last week, I finally attended my first #AECTechCon on May 7 and 8 at the St. Charles Convention Center in St. Charles, MO, just outside St. Louis. This event had been on my radar for a while, and it did not disappoint. It offered a solid mix of learning and knowledge sharing around AEC tech, plus a strong expo hall. The usual suspects were there, along with some standout locals and a few new-to-me gems (you really need to check out iPlanTables).

The keynotes were strong, the cornhole tournament was chaotic in the best way, and the schedule left room to network or catch your breath after a long day of sessions, booth duty, or both.

Keep reading for a look at my session from the conference and why I think this one belongs on your 2026 must-attend list.

Continue reading “#AECTechCon, Low-Code & AI, Oh My!” →
100 Days of AI, AEC, AECO, AI, BIM, Coding, Learning, VDC

100 Days of AI – Phase 3 Recap

The BIMsider

As we dive into the third phase of the #100DaysOfAI challenge, things are getting interesting! We’re building on the strong AI foundations and exploring cool use cases from earlier stages. This phase is all about putting our new AI skills to the test on “real-world” problems and pushing the limits of what we can do with the tech we’ve gotten the hang of. Come along as I chat about the adventures and breakthroughs in this final stretch, where we’re turning theory into practice and learning into some seriously cool innovation.

Continue reading “100 Days of AI – Phase 3 Recap” →