AI Didn’t Kill the Web, It Moved in!
summary
Demos show concrete features and whether they work: a browser-embedded MCP server lets agents call tools, Chrome DevTools debug with AI pulls console, network and trace data and suggests fixes, the repo’s .agent/skills drive coding agents and call Playwright CLI to record videos and send a Telegram link, on-device Web AI APIs (summarize, proofreader, prompt) download ~4 GB models and run locally, LLMs.txt and Web MCP register tool schemas on pages so agents can add-to-cart or submit forms — mostly functional though tokens and alpha flags sometimes break flows.
AI-written summary · about
chapters (10)
- 0:00AI on the web
- 1:04AI in web development
- 3:13Live coding agents demo
- 7:49Debugging with AI DevTools
- 15:59Upgrading to agent workflows
- 23:27AI in browser apps
- 30:26Using local AI APIs for summarization and proofreading
- 36:03Optimizing for AI agents
- 40:14Web MCP introduction
- 51:15Summary and future
related talks
24mState of client side AI
39mThe AI PC and the Era of the Modern Web
02mDiscover Web AI: Client side Agents, Gen AI, and machine learning in the browser
11mDon't let AI agents push your buttons - use webMCP instead!
23mWebAI: Building the next user experience in the browser
21mUnlocking Client-Side AI in Your Web App
29mClient side Web AI Agents Building smarter user experiences for a future age
30mLook ma, no hands! Multimodal AI-Agents in the browser