Google announced that it"s bringing its no-code AI mini-app builder, Opal, to more countries as part of the latest expansion and updates. Among the top-requested features for the AI app builder, users have asked for more transparency and reliability in Opal workflows.
Opal was launched a couple of months ago as an early experiment in Google Labs in the US. People can use the tool to develop AI-powered mini-apps using natural language prompts, without having any coding knowledge.
They can use conversational editing to describe their idea and logic in plain English and make the necessary modifications. They can build multi-step apps by chaining prompts, AI model calls, and other tools, and make edits in the visual editor.
Opal is powered by Gemini 2.5, Imagen 4, AudioLM, and Veo models. It converts an app description into a multi-step workflow with inputs, generation steps, and output steps. People can also use the tool to conduct in-depth research on a topic, draft a blog post, and create a video to accompany the mini-app.
It is now rolling out to more than a dozen new countries, including Canada, India, Japan, South Korea, Vietnam, Indonesia, Brazil, Singapore, Colombia, El Salvador, Costa Rica, Panamá, Honduras, Argentina, and Pakistan.
Google said in a blog post that it"s rolling out advanced debugging for Opal workflows. Users can run their workflows step-by-step in the visual editor or iterate on a specific step in the console panel. The errors are displayed in real-time and localized to the exact step where the failure occurred, potentially saving some time during the debugging process.
The search giant has made updates behind the scenes to improve the core performance for the AI app builder. The tool is now faster to get started and reduces overall wait times with parallel runs to simultaneously execute complex workflows with multiple steps.