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.
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.