GDG Coding Jams
Build with AI. Together.
Share
← Back to the lineup
Track 01

Glow Up

Selfie + a hairstyle → see the new you.

✅ Drop-in friendly2-hour jamShips in 45 min
The demo

What it looks like when it’s working

In the room · 45 minutes

What you’ll build

Upload a selfie. Pick from preset hairstyles. AI does a virtual hair try-on via Vertex AI image generation — same person, new look — and shows before / after side by side.

The moment it clicks

OMG that's me with bangs.

Things to think about

While you build

  • Hair only today. No outfits, no facial filters — those are the polished version. The constraint is what gets you to ship.
  • Your signature detail is what makes your app yours. A sassy stylist note? A vibe rating? Decide before you start typing.
  • Test on a face you don't recognize first. You'll catch prompt issues faster when there's no emotional read on the result.
The 2-hour Jam rhythm

How the night flows

Every Coding Jam follows the same five-phase shape. Talking is short, building is long.

  1. 0:00 – 0:05
    Intro

    Welcome, name tags, snacks within reach. The facilitator sets the tone: low pressure, high creativity, ship something messy.

  2. 0:05 – 0:15
    The Demo

    Facilitator demos the polished version of tonight's project. Live or pre-recorded. The message: this is what's possible.

  3. 0:15 – 0:25
    Spec Talk

    Walk the 5 questions on the projector. The output is a one-page PRD that Antigravity will turn into UI + engineering docs.

  4. 0:25 – 1:30
    Build (codelab)

    Participants run the codelab. Antigravity writes the code; they direct it. Six phases inside this hour: Setup → Plan → Review → Build → API → Verify. Fix the doc, not the code.

  5. 1:30 – 2:00
    Sharing

    Three volunteer screen-shares. Celebrate the messy, brilliant, half-finished prototypes. Quick wrap-up. Tease the next jam.

Polished version pulls in

Where to take it after the jam

The 45-minute build is the win in the room. These are the ideas you can pull in over the next week — your homework isn’t homework, it’s the polished version.

  • Outfit and accessory modes
  • Custom typed-in prompts
  • Share button
  • Side-by-side compare
  • Lookbook to save favorites
  • 'Rate my friends' group photo
  • Decade time machine
If you get stuck

Open one of these in the starter — safety nets, not requirements.

  • context/image-gen-tryon.md
From the community

Builds shipped from this track

All builds from this track →
Vibe Style
Track 01GDG Brooklyn
Vibe Style

This app is a conversational AI stylist for your closet: it asks about your mood, who you’re dressing for, and the occasion (or trip details), then generates complete, head-to-toe outfits pulled from your own digitized wardrobe — shown as e-commerce-style look cards with Add to Bag, Favorite, and Customize options. It also handles multi-person trip packing (partner/family), weather-aware travel essentials, and destination-only shopping suggestions, all wrapped in a friendly “best friend stylist”

I assumed the hard part would be the styling logic. It wasn’t, the hard part was getting the AI to remember it already knew you were shopping solo, and to stop asking.

Film Room
Track 01GDG Brooklyn
Film Room

Film Room turns a phone video of one pickup basketball possession into a coach's breakdown — annotated video, real spatial analytics, and a bridge to the NBA action it resembles — so you learn to read the game by studying your own film.

The model turned out to be far better at reading basketball than at telling my friends apart — it diagnosed the blown switch instantly but couldn't reliably say who blew it, which forced me to design the whole system so the tactical read still holds when player identification fails.

ISLE-VIEW-MOLLY
Track 01ISLE-VIEW-MOLLY
ISLE-VIEW-MOLLY

AURADEX is an AI-powered desktop productivity application built with Electron and modern web technologies. It provides an interactive workspace with analytics, project management tools, and AI-assisted features in a single interface. The goal is to help users stay productive while managing projects efficiently.

I expected the hardest part to be building the interface, but integrating multiple features into a smooth desktop experience was the bigger challenge. I also learned that small performance optimizations can significantly improve the user experience.

Pick another track

All independent — start anywhere.

See full lineup →