Google LabsがOpalに自律的AI機能を追加

2 Min Read

Google Labs introduced a new feature for its vibe-coding app Opal, an interactive agent that plans and executes tasks based on a user’s goal.

The update turns Opal from a static tool to an agentic model, Google said in a blog post on the launch. Google Labs is the tech giant's public testing ground for new and experimental products.

The app previously consisted of predefined steps, requiring developers to manually specify the input and model required for the task.

With the upgrade, released on Feb. 24, Google is automating that process, with the agent designed to “understand your objective” and automatically determine the best models and actions to achieve it.

“We believe this approach gives you the best of both worlds,” Google said. “The power of an AI agent working towards your goal and the control of a step-by-step workflow you can customize and refine at any time.”

Using the Gemini 3 Flash model, the updated model can remember information across sessions to more effectively plan and execute tasks, tailoring responses and creating, according to Google, a more personalized experience.

Related:AWS Bets on Frontier Agents as the Next Era of Enterprise AI

For example, Google highlighted an executive briefing workflow in Opal, in which the agent adjusts the content depending on whether the user is meeting a new or an existing client.

Opal can now search the web for background information on new prospects or review internal meeting notes to provide relevant context.

The new agents are also natively interactive, Google said in the blog post. If additional details are required, the system prompts users for clarification or presents options to guide the next steps, rather than relying on pre-set workflows.

The vendor said the enhancement enables even non-technical users to build more complex, multi-step workflows within their apps.

Google first introduced Opal to U.S. users in July 2025 as a tool for creating mini web applications or remixing existing ones without writing code. The tool expanded to 15 more countries in October 2025, before rolling out to more than 160 markets a month later.

Google is not alone in its focus on vibe-coding; major AI vendors such as OpenAI and Anthropic are also rolling out similar systems as customers favor easy-to-use, intelligent models.

About the Author

Contributing Writer

Scarlett Evans is a freelance writer with a focus on emerging technologies and the minerals industry. Previously, she served as assistant editor at IoT World Today, where she specialized in robotics and smart city technologies. Scarlett also has a background in the mining and resources sector, with experience at Mine Australia, Mine Technology and Power Technology. She joined Informa in April 2022 before transitioning to freelance work.