How Web Apps Are Evolving into AI Agents
summary
Argues web interfaces evolve into autonomous apps by combining retrieval, function-calling and tool access into agent logic and shows a working Node.js agent built with Google ADK that runs in a terminal and a debug web UI, calls Gemini models via Gemini via Google AI Studio, uses RAG and memory for current, personalized answers, and deploys to Vertex AI/Cloud Run; code lab reproduces the steps and the sample agent runs end to end.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 1:03AI ecosystem and Gemini models
- 3:53Google AI Studio for developers
- 9:10AI agents and capabilities
- 15:30Building AI agents with Google ADK
- 23:15Deployment options
- 25:45Resources and next steps
- 28:13Q&A
related talks
22mClient side Web AI Agents: Building smarter user experiences for future agentic ...
21mUnlocking Client-Side AI in Your Web App
15mThe future of AI is now: Real-life case studies for on client-side AI adoption in web apps
49mLet's build an AI agent
14mThe New Web Is Agentic. Is Your Infrastructure Ready?
53mAI Didn’t Kill the Web, It Moved in!
29mClient side Web AI Agents Building smarter user experiences for a future age
58mAI Agents Will Change How We Build the Web