Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Assistant Shell: Client-Side AI Chat
Learn how I built a clientâside AI chat PWA using only AI assistants, without any backend code, with a live demo and development insights.
What if you could build an entire AI-powered web chat app without writing a single line of code yourself?
Thatâs exactly what I did!
Assistant Shell đ¤đ is a sleek, no-install AI chat app that lets you talk to every major AI Assistant â OpenAIâs GPTs, Anthropicâs Claude, Googleâs Gemini, even local models via Ollama, and even more.
You just drop in your API keys, tweak your settings, and boom â youâre chatting with AI on your terms.
But hereâs the real kicker: I built the whole thing using only AI Assistants.
Every bit of code of Next.js, TypeScript, TailwindCSS was written with ChatGPT, Claude, Gemini, Copilot, Continue, and Cline.
Furthermore, the app has no backend, no server storing your conversations, no other data collection â just pure, client-side AI magic.
Last but not least, this web app is also a PWA so you can âinstallâ it with one click on any device!
Assistant Shell provides a command-line interface for AI assistant interaction.
Browser PWA unifies multi-model AI, local keys, instant switching, no subscriptions.
Related projects
Beyond the Prompt: Building Chatbots That Control Your UI
Hamburg
Learn how to integrate a chatbot that directly manipulates a frontend, using inâchat UI components and automatic pageâŚ
AI curated whatsapp memories
Cologne
Learn how to extract, rank, and store the most memorable WhatsApp messages using a Python script, Gemini 2.5âŚ
1nterface ai
ZĂźrich
The talk explores an AI-driven context collection tool designed for laptops, demonstrating how it understands user behavior toâŚ
Finally, an AI support agent that asks you when it doesnât know
Munich
This talk covers building AI support agents that recognize their limits, ask for help when uncertain, and prioritizeâŚ
Meal Planner
Hamburg
Learn how to build a mealâplanning system with LangGraph, combining AI agents, chains, and persistent memory to adaptâŚ
ProductBar: Using AI to identify ideas in customer feedback
Hamburg
A walkthrough of ProductBar, an AI system that categorizes customer feedback, demonstrates its analysis workflow, and explores implementationâŚ