Playground · AI-Assisted Build
How AI tools enable designers to ship functional products — without a single developer in the room.
Quick note: This is a speed experiment, not a polished case study. The point isn't the app itself — it's what the process reveals about the future of designer autonomy. For deeper work, see the Candidly case study →
01
Every Christmas, my family runs a Secret Santa — split between Portugal and Brazil. We used to draw names from a hat, which meant someone had to physically coordinate it. With family on two continents, that stopped working.
The obvious solution is one of the dozen Secret Santa apps out there. Except: they all require account creation, collect more data than necessary, and none of them support our actual tradition — which includes our dogs, Canela and Baunilha, as participants. (Yes, the dogs do Secret Santa. Don't judge us.)
Paper method
Can't share remotely without spoiling the draw
Existing apps
Require accounts, collect data, no pet support
Manual coordination
Someone always accidentally sees who got who
The real challenge underneath all of this: could I — a designer with no coding background — actually ship a working product solo? Not a prototype. A deployed app with a real URL.
02
Before building, I mapped what already existed. Claude helped me structure this analysis quickly.
| App | Account Required | Pet Support | Shareable Link | Wishlist | Free |
|---|---|---|---|---|---|
| Elfster | Yes | No | Yes | Yes | Freemium |
| DrawNames | Yes | No | Yes | Yes | Freemium |
| Secret Santa Organizer | No | No | No | No | Yes |
| Giftster | Yes | No | Yes | Yes | Freemium |
| My Secret Santa App ✦ | No | Yes | Yes | No | Yes |
The gap was clear: zero-friction, no-account, pet-friendly, shareable links. Simple scope that any competent tool could solve — which was exactly the point.
03
The actual sprint happened while my wife was in the room — she doesn't know how to do this, and I wanted to see if I could ship something real before she noticed I was building instead of watching TV.
01
Claude
Ideation & Planning
Scoped the problem, mapped competitive landscape, defined constraints, audited my own thinking
02
Claude
Product Audit
Stress-tested decisions: minimum participants, grouped pets logic, edge cases
03
V0
Build
Described the app in plain language. V0 generated Next.js + shadcn/ui. Iterated 2-3 times.
04
Vercel
Deploy
Connected GitHub repo, one-click deploy. Got a real URL. Done.
Best for structured thinking. I used it like a product manager — it pushed back on assumptions, helped me think through edge cases, and surfaced decisions I hadn't considered. The dialogue format maps well to how designers think through problems.
Best for UI generation. Vercel's tool speaks designer — you can describe layout, component style, and interaction in natural language and get production-quality React code. It uses shadcn/ui which has solid defaults.
Lowest friction deployment I've seen. Connect a GitHub repo, it builds and deploys automatically. For someone who's never deployed anything before, this was genuinely magical.
04
This wasn't just "describe app, get app." There were real product decisions to navigate — and Claude became a thinking partner, not just a code generator.
The question: If Canela and Baunilha are participants, they need a human to receive on their behalf. How do you model that without making the UX confusing?
Resolution: Owner-pet groups: pets are linked to an owner and excluded from drawing with their owner's group. Simple rule, clear UX.
The question: What's the minimum viable draw? 2 people? 3? If 2 people draw names, it's deterministic and pointless.
Resolution: Minimum of 3 participants required before the draw can happen. Claude helped me think through the math.
The question: Every competitor has wishlists. Should we?
Resolution: No — scope discipline. A wishlist would double the UX surface area for a v1 speed experiment. Cut it without guilt.
The question: After drawing, how does each person see who they got without everyone seeing everyone else's result?
Resolution: Unique URLs per participant. Each person gets a private link that reveals only their assignment.
The most useful part wasn't asking Claude to generate — it was asking Claude to challenge. I'd describe a decision and then ask: "What am I missing? What edge cases break this?"
This is actually closer to how designers should work: define the problem, propose a solution, stress-test it. AI accelerates the loop, but the judgment calls are still yours.
What worked well
What didn't
05
App screenshot
Add your screenshot to /public/images/ and update this section
Secret Santa for Pets — live at secret-santa-psi-five.vercel.app
Add humans and pets, group pets with their owners
Owners never draw their own pets; configurable exclusions
Algorithm handles constraints automatically
Each participant gets a unique private link to their result
One-tap share to send results directly in chat
Zero friction — open the link, do the draw, done
06
Before AI tools, a designer with an idea had a clear ceiling: Figma. You could design the solution, document it, hand it off, and then wait. Weeks, sometimes months. The gap between idea and shipped product required a developer to cross.
That gap is collapsing. Not for everything — complex systems, performance-critical code, serious production applications still need expert engineers. But for MVPs, prototypes, internal tools, proof-of-concepts? Designers can now ship.
This isn't about replacing developers. It's about what happens at the boundary — when a designer has a validated idea and needs to test it in the real world, not just in Figma.
Before
Had an idea → designed in Figma → handed off → waited → hoped
Now
Had an idea → validated with AI → built with V0 → deployed → learned
Before
Dependent on developers for any real-world validation
Now
Can validate independently, then bring developers in for scale
Before
Advocate for the user in meetings
Now
Advocate with evidence — because you shipped something real
The app works. It was used. But if I spent another hour on it: I'd add a constraint UI so organizers can set exclusions without thinking about the underlying logic, and I'd add a simple history view so you can reference last year's draw.
But that's the point — you learn what to improve by shipping, not by planning. This experiment was worth the 5 minutes.