The Invisible Workforce: AI Agents Behind the Scenes
summary
Distinguishes planning vs execution by defining agentic AI as the planner and AI agents as the executors, lays out perception/cognition/action modules, and demos a working PPT generator built with Google’s ADK using the A2A protocol and Gemini 2.0 oflash: a Wikipedia agent extracts page text into an output_key and a PPT agent consumes that state to produce a slide deck on James Gosling. Shows code structure, custom tools, and three run modes (adk web, adk run, adk fastapi).
AI-written summary · about
chapters (7)
- 0:00Introduction to AI agents
- 3:29Core building blocks of AI agents
- 6:58Types of AI agents
- 11:15Frameworks for building agents
- 14:05Model Context Protocol explained
- 17:39Demo: ADK agent creation
- 23:45Conclusion and Q&A
related talks
01h 23mBuild your own AI Agent
29mWhat exactly are AI Agents?
22mAgentic AI for Engineering Leaders | Strategy & Execution Guide
37mAI Agents: The New Era of Intelligent Software
45mUnifying AI experience for customers: Building multi-agent systems with Google ADK
27mAgentic Engineering: Working With AI, Not Just Using It
29mAgentic AI: What It Is and Why It Matters
35mAI Agent and the Promotion You Didn't Ask For