• Open Doors
  • Posts
  • What Should You Even Vibe Code? 👀

What Should You Even Vibe Code? 👀

Three types of projects that help you learn AI, show literacy, and make your portfolio more compelling.

In partnership with

Hey and welcome back to a new week!

First thing I’d love to announce the winners of the tickets for Prompt to Product from last week’s raffle:

Raquel P.

Regina M.

The winners were contacted via email prior to this email so in case you are one of the winners and reading it here for the first time, make sure to check your emails.

Congratulations! I hope you have a blast and learn a lot on May 18!

In this issue:

  • You Want To Vibe Code. Now What? Picking what to put these new possibilities to use for is sometimes harder than actually doing it. I’m here to help.

  • Joanna’s Portfolio: Another excellent example of how to pull off a multidisciplinary portfolio.

Thank you for reading!

🤖 GET ALL THE AI NEWS YOU NEED

Become An AI Expert In Just 5 Minutes

If you’re a decision maker at your company, you need to be on the bleeding edge of, well, everything. But before you go signing up for seminars, conferences, lunch ‘n learns, and all that jazz, just know there’s a far better (and simpler) way: Subscribing to The Deep View.

This daily newsletter condenses everything you need to know about the latest and greatest AI developments into a 5-minute read. Squeeze it into your morning coffee break and before you know it, you’ll be an expert too.

Subscribe right here. It’s totally free, wildly informative, and trusted by 600,000+ readers at Google, Meta, Microsoft, and beyond.

What Should You Even Vibe Code? 👀

You hear a lot about why designers should try AI tools and vibe coding. Fair. I’ve been saying the same thing. I’ve also been showing people how to do it in workshops.

I do realize though that the first blocker people face isn’t the tool choice or anything it is the question what to build in the first place.

That part is less obvious than it sounds for many.

And it matters, because building things with AI does a few useful things at once. It shows literacy, yes. But more importantly, it teaches you by doing. You learn AI by using AI. You start to understand what these tools are good at, where they fall apart, how to prompt better, how to scope better, and how to move from an idea to something tangible.

And once that clicks, a lot of things that previously felt out of reach suddenly don’t.

So if you’re wondering where to start, I’d put most vibe-coded projects into three buckets.

1. Build something directly tied to a project you already have

This is the most tangible category, and probably the easiest one to make useful inside a portfolio.

Take something that already exists in your work and push it one step further.

That could be:

  • a functional prototype

  • a coded flow from a past project

  • a component library or design system brought out of Figma and into code

  • a fictional case study turned into something people can actually interact with

This works well because a lot of design work still stops too early.

You designed the thing.

You maybe prototyped it in Figma.

And then it stayed there.

Now you can go back and build part of it for real.

That immediately makes the project feel more grounded. It also forces you to deal with behavior, states, and edge cases that static screens hide very well. And if you pick something slightly more complex, the scoping part becomes valuable too. Choosing the right slice to build is a product skill in itself.

Where this goes in your portfolio

This is usually easiest to weave into an existing case study.

For example, somewhere in the lower half of the project, maybe before the outcome, you add a small section like:

2026 update: functional prototype built with AI

Then you briefly explain what you built, why you picked that part, and what changed once it became interactive. Ideally, you link out to it so people can try it.

That’s the key here.

Don’t only talk about it.

Host it.

Link it.

Let people touch it.

2. Build something fun, personal, or playful

This category is less about utility and more about range.

It gives you room to explore things that don’t always fit neatly into a normal portfolio project. Personal voice. Visual atmosphere. Interaction craft. Playfulness. Taste.

A very good example is Rita Wang’s Nightbus Station. She built a project around sleepless nights and the thoughts that keep you awake, tied to personal memories. Functionally it’s not huge. That’s not the point. The point is that it feels thoughtful, personal, and visually very well done.

Such a thoughtful project with excellent execution!

Another one I love is Harsha Gowda’s Girlfriend Guide. It’s basically a playful little notebook app with beautiful page-flip interactions and a fun concept. It was a small project, but it was done with so much care that it became memorable immediately.

Flip the pages here - so satisfying!

Then there are things like Justin Shi’s Pokédex and smaller widgets in his portfolio. Some lean more playful, some connect more directly to what he can do work-wise, but that overlap is part of why they land.

No need to build fully-fledged apps - sometimes a small widget is enough to showcase your skills

This category works when the project feels deliberate and well executed.

It does not need to be huge.

It does not need to solve a giant problem.

It does not need to become a startup.

It needs to show taste and care.

Where this goes in your portfolio

This belongs in your playground section or in a slightly separated section right underneath your main work.

That separation matters.

You don’t want these projects to compete too hard with your core case studies. They are there to add contrast, show craft, and make the portfolio feel more alive. Not to carry the whole thing.

And again, if possible, host them properly and link out to them. These projects gain a lot when people can actually click into them instead of only reading about them.

3. Build something genuinely useful

This is probably the category where the dots connect most naturally.

Start with yourself here, not with some imagined audience.

What do you keep running into in your day to day?

What workflow annoys you?

What do you do manually over and over?

What tool almost works for you, but never quite gets there?

That’s where a lot of good projects come from.

For example, I built a task tracker for myself because the setup I had in Notion stopped being enough once I was able to make something more tailored. Same with a finance tracker for Open Doors-related work. These aren’t glamorous projects. They are utility. But that’s precisely why they make sense.

Another example from my own work is the Figma plugin I built for GriddyIcons. That was before vibe coding became as structured as it is now, and it was a great learning experience. Building plugins is much easier now, which makes this a very good lane if you have a useful idea tied to tools designers already use.

I built this with ChatGPT as my sidekick before Cursor, Lovable and Claude Code existed. I went through a lot of pain but I’m glad I did ha.

That’s also why I like examples like Airla Fan’s (upcoming) PixelPal, which tackles a problem she saw inside Adobe Express through a plugin. There’s a clear reason for it to exist.

And then there are projects that sit somewhere between useful and playful, like Xiaoyang Hu’s design-resource X clone. That one has a clearer use case, but still feels light and fun.

A super cool way to build something that even tells its own story

That overlap can be a very good place to be.

Where this goes in your portfolio

This depends on how far the project has gone.

If there was a decent process behind it, if you’ve put proper thought into it, if people are using it, or if you’re even selling it, then yes, it can absolutely deserve to become a proper case study. At that point, it makes sense to talk about it from a business angle as well.

But if you vibe coded it last week, one person used it, and you’re mostly excited that it exists at all, then don’t overinflate it.

Then it still belongs in your playground.

That distinction matters.

Not every useful project needs to be framed like a serious product case study. Some are still early explorations, and that’s fine. The project does not become weaker because of that. It only becomes awkward if you try to present it as more mature than it is.

Bonus: your own portfolio

This one is obvious, but it still deserves a mention.

If you are deeply unhappy with your current portfolio and feel limited by the setup, you could absolutely vibe code your own portfolio.

That is obviously a bigger project. It is not the same kind of thing as a small weekend experiment. And in many cases, I would still say people already have enough flexibility with tools like Framer.

But if you have a clear idea and want the freedom to shape the whole thing more fully, then yes, your portfolio itself can become the project.

At that point, though, it is the project.

Not a little extension. Not a partial rebuild. The whole thing.

So I would only go there if you genuinely want that challenge.

Start smaller than you think

That’s probably the main thing I’d leave you with.

You do not need to build the next big thing.

You do not need to prove that you can make a startup.

You do not need to overcomplicate this.

A good vibe-coded project can be:

  • a prototype tied to old work

  • a small personal experiment

  • a playful side project

  • a useful internal tool

  • a plugin that solves one annoying problem

What matters is that it fits your current level, teaches you something, and gives people a clearer sense of how you think.

That is already a lot.

And in most cases, the better move is to start smaller than you think and do that one thing with care.

MY FAVORITE SOURCE OF NEWS 📰 

A free newsletter with the marketing ideas you need

The best marketing ideas come from marketers who live it. That’s what The Marketing Millennials delivers: real insights, fresh takes, and no fluff. Written by Daniel Murray, a marketer who knows what works, this newsletter cuts through the noise so you can stop guessing and start winning. Subscribe and level up your marketing game.

👀 Portfolio Showcase

Joanna Ni’s portfolio is one of those where you open it and there’s a slight disconnect. Not in a bad way. More like… this shouldn’t feel this put together yet.

She’s still studying at Carnegie Mellon University, but the work doesn’t behave like student work. It’s not trying to impress. It just… holds.

What stood out immediately is that she’s not trying to fit into one lane. Motion, product, brand, web. All there. And usually that’s exactly where things start to break. You see someone being good at one thing and then stretching into others a bit too early.

That’s not what’s happening here.

That’s it for this week—thanks so much for the support! ♥️

Do you want your own portfolio reviewed in-depth with a 30-minute advice-packed video review? Or do you require mentoring to figure out a proper strategy for your job search?

I got you!

Keep kicking doors open and see you next week!
- Florian