Most AI workshops end where the interesting part begins...
You've built the chatbot.
You've prompted the model.
Now what?

What if your AI application could see a room, interpret a gesture, or react to someone's mood in real-time? What if coding felt less like syntax wrestling and more like conducting an orchestra?

Join GDG Web Stockholm for an immersive, hands-on workshop at Google’s Stockholm office where we go beyond chatbots and start building multimodal AI experiences.

This isn't about following steps — it's about architecting multimodal experiences that blur the line between intelligence and interaction.
What makes this different?
→ Move from text prompts to vision, gestures, and real-time systems
→ Master AI-native workflows with Gemini, AI Studio, and Antigravity
→ Build what you imagine: mood-reactive organisms, gesture-controlled particles, or camera-based games
→ "Vibe code" your way through creative constraints (yes, that's a thing now)

This is for developers ready to break out of the chatbot box and explore what happens when AI meets the physical world.

Schedule:

• 12:00-13:00 – Check-in, lunch, and networking

• 13:00-15:00 – Part 1 – Foundations
  Learn AI-native workflows with Gemini, AI Studio, and Antigravity. Craft better prompts, work with structured outputs, and “vibe code” a small logic engine to get your setup ready.

• 15:00-15:30 – Coffee break

• 15:30-17:00 – Part 2: Building with Firebase and AI integration
  Choose your own path and build an interactive project—such as a face-reactive experience, gesture-controlled visuals, or a camera-based game. Iterate in real time using natural language and creative coding with Three.js or Canvas.

• 17:00-17:30 – Wrap-up and venue departure

Please bring:

• A laptop

• Node.js & Git installed

• Gemini CLI

• Google Antigravity set up

⚠️ Spots are limited. If you've been waiting for a reason to push beyond basic implementations, this is it.