In this video, we look at the recent updates to Google's Opal agent system. How it's now set up to take advantage of the Gemini 3 models and how you can use it to build simple apps and agents 

Blog: https://blog.google/innovation-and-ai/models-and-research/google-labs/opal-agent/

For more tutorials on using LLMs and building agents, check out my Patreon
Patreon: https://www.patreon.com/SamWitteveen
Twitter: https://x.com/Sam_Witteveen 

🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes

👨‍💻Github:
https://github.com/samwit/llm-tutorials

⏱️Time Stamps:
00:00 Intro
00:40 Google Labs
02:40 Opal: Agent Step Blog
05:49 Opal: New Tools
07:57 Demo

Sam Witteveen AI is a publication offering insights, tutorials, and resources for artificial intelligence (AI) enthusiasts and practitioners. Readers can learn about machine learning algorithms, deep learning frameworks, and AI applications. With tutorials, case studies, and expert interviews, Sam Witteveen AI provides  guidance and expertise for building and deploying AI solutions.

Sam Witteveen

Google Labs has updated Opal, its no-code visual agent builder, with several new capabilities that reflect broader trends in AI agent development. Key additions include an 'agent step' that lets the model dynamically determine its own path rather than following rigid predefined workflows, cross-session memory so agents grow smarter over time, dynamic routing through decision graphs, and human-in-the-loop interactive chat. These features mirror patterns seen in developer tools like LangGraph and OpenClaw but packaged for non-technical users. A walkthrough demonstrates building a Tokyo events finder app entirely through natural language, with no coding required. The update is free to use and agents can be published and shared via the Gemini app.

Google's Agent Upgrade