Hajra Naz
Google announced Tuesday that it is introducing a new way to build automated workflows inside its low-coding app, Opal.
The update adds a new AI agent to Opal that enables users to create mini-apps capable of planning and executing tasks through simple text prompts. Instead of manually configuring each step, users can describe what they want the app to do — and the agent handles the rest.
Gemini 3 Flash powers the feature and can automatically select the appropriate tools needed to complete a task. For example, it can connect with Google Sheets to store information between sessions, such as maintaining a shopping list for an e-commerce app. The agent doesn’t just execute instructions — it also determines the next steps on its own.
Google says these agents are designed to be natively interactive. If additional details are required, the system will prompt users for more input or present options to guide the workflow forward. The company claims this makes it possible for people without technical expertise to build complex, multi-step applications with minimal effort.
Opal first launched in the U.S. in July 2025, allowing users to create simple web apps or remix existing ones. In October 2025, Google expanded availability to 15 additional countries, including Canada, India, Japan, South Korea, Vietnam, Indonesia, Brazil, and Singapore.
By November, the tool was accessible in more than 160 countries. In December, Google integrated Opal directly into the Gemini web app, enabling users to build custom apps through a visual editor without writing code.
Google’s move comes as competition intensifies in the growing AI-powered app-building space. Startups like Lovable and Replit have gained traction with natural-language development tools. Others, including Wabi, Emergent, and Rocket. new, are also emerging as notable players in the space.
With this latest addition, Google is positioning Opal as a more capable, accessible platform for building automated applications using AI.
