Author: Google Cloud Tech – Duration: 00:08:29

Follow the programming workshop → https://goo.gle/3Q5TSt3

GitHub repository → https://goo.gle/4fsahT8

Google Agent SDK (ADK) → https://goo.gle/3Q3enqf

At the simplest level, an AI agent doesn't just respond: it decides and acts. In this video, Smitha goes beyond basic chatbots and demonstrates how to build a fully autonomous, self-correcting multi-agent system from scratch using Google's Agent Development Kit (ADK). First, Smitha breaks down the theory behind modern agents: the ReAct framework (reasoning and action) and the 3 main agent models (sequential, reactive, and planning). Then she jumps straight into Python to create a handy *blog writer agent*. Watch and learn how to combine *Planner* and *Writer* agents with validation checkers and loop agents to create an AI that detects its own errors and automatically retries until it succeeds. Chapters: 00:00 – Explanation of AI agents 01:05 – Explanation of the ReAct framework 02:15 – The 3 types of AI agents (sequential, reactive, planning) 03:30 – Project presentation: the auto-correct blog editor 04:15 – Configuring Google ADK and UV 04:50 – Coding the scheduler agent 05:40 – Adding a correction automatic (Validation Checkers and Loopback Agents) 06:50 – Coding Blog Writer and Root Agent 08:20 – Testing AI in ADK Web UI 09:40 – What’s Next? (Connecting to MCP servers) More resources: ReAct Paper → https://goo.gle/4oa1oQ9

🔗 Connect with Smitha online: YouTube → https://goo.gle/Smitha-on-YouTube

Linkedin → https://goo.gle/Smitha-on-LinkedIn

X → https://goo.gle/Smitha-on-X

#AIAgents #GoogleADK #PythonTutorial #SoftwareEngineering #MachineLearning #LLMs Watch More Modern AI Agents: From Theory to Production → https://goo.gle/Learn-with-Smitha

🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech

#AIAgents #Gemini Speaker: Smitha Kolan Products Mentioned: Agent Development Kit, Gemini