Google Unveils Opal: AI-Powered No-Code App Development Tool

Google's new AI tool Opal turns prompts into apps, no coding required

Historically, building an app required an intimate understanding of the intricacies of writing code. Thanks to AI, those days are over. Google unveiled Opal, an experimental tool out of Google Labs that allows developers to create apps using natural language prompts and interactive visual aids, Thursday. Opal harnesses a suite of Google's proprietary AI models to help users create various visual assets for their apps. Gemini 2.5 can assist with the written copy for a blog post, for example, while Veo 3 and Imagen 4 can generate accompanying videos (including audio) or images, respectively. Also: Google's new Search mode puts classic results back on top - how to access it "We want to deliver a product that gives users more control and transparency over combining all the capabilities of Google models, without having to code," Elle Zadina, a product manager with the company, said in an online demo video. The feature offers a gallery of premade app templates, each with its own aesthetic, similar to those offered by website-building platforms like Wix and Squarespace. They're also tailored to different creative needs: one lets you build immersive virtual games, for example, and another is geared toward generating video ads for a specific audience. You can also start from scratch by clicking the "Create New" window above the template gallery. This will direct you to a simple prompt window, where you can describe in natural language a rough overview of the function you'd like your app to perform. Your instructions will be converted into an illustrated workflow, organized by inputs (what you've requested), generation steps (the specific steps the models are taking to design the app), and output (the final, amalgamated product). Each step appears as a separate box, which you can click to see the specific actions the models are taking or add your own edits directly. There's also a "Share app" option in the top-right corner of the screen in Opal, through which you can toggle your app from private to public and share a URL with anyone with a Google account. Opal is available now for US users in public beta -- you can access it here. Also: I got ChatGPT Agent to deliver a truly useful report - and then NotebookLM took it to the next level This release comes just one day after Microsoft-owned GitHub launched Spark, a similar app-building platform, in public preview. These systems are part of a broader trend throughout the tech industry toward "low-code" and "no-code" tools, which harness AI to automate many of the key steps in the software development process. Get the morning's top stories in your inbox each day with our Tech Today newsletter.

Google Labs introduces Opal for developing AI mini apps

Now in public beta, developers can use Opal to build and remix AI mini apps using conversational natural language commands, a visual editor, or both. Google Labs has announced the public beta of Opal, an experimental tool for building AI mini apps by chaining together prompts, tools, and models, using natural language and visual editing. Currently available in the United States only, Opal was introduced July 24. The tool can be used to accelerate prototyping of AI ideas and workflows, demonstrate a proof of concept, or build custom AI applications to boost productivity. Opal is billed as an experimental product exploring the future of building with AI models and prompts. The beta release includes a demo gallery with starter templates that can be used as-is or remixed to fit specific needs. Opal lets developers bring prompts to life with no code required, according to Google Labs. The tool helps simplify workflows, empowering users to build multi-step apps by chaining together prompts, AI model calls, and other tools. Developers simply describe the logic, and Opal will build a visual workflow. Opal also translates instructions into visual workflows for editing, providing fine-grained control without the need to review a line of code.

Google debuts no-code Opal tool for building 'AI mini apps' - SiliconANGLE

Google LLC has introduced an artificial intelligence tool that enables users to build simple applications without writing any code. The tool, which is known as Opal, made its debut on Thursday. The launch comes a few weeks after Amazon Web Services Inc. introduced an IDE, or integrated development environment, called Kiro that uses AI to speed up software projects. The starting point of an Opal development project is a ChatGPT-like chatbot interface. Users enter a natural language description of the task their application will perform. They can also provide any additional data that may be needed to complete the task, as well as connect external tools. The service uses the provided data to automatically generate a simple application. Once the software is ready, users can share it through a button at the top right corner of the interface. It makes the application accessible through a sharing link similar to those used by Google Docs. Optionally, workers can edit an Opal-generated application before publishing it using a visual editor. The editor represents an application as a collection of cards on a virtual canvas. Some of the cards describe the input the application ingests, while others control how it processes that input. The visual editor makes it possible to link together multiple data processing steps. For example, a user could have an application generate a product description and then create a promotional video based on that description. Workers can customize how such tasks are performed by entering natural language instructions via Opal's visual editor. "Opal converts your app description into a multi-step workflow with inputs, generation steps and output steps," Google product manager Elle Zadina explained in a demo video. "You can click into a step to see the prompt or instructions and edit them directly." Under the hood, Opal relies on multiple AI models to generate applications. Google didn't specify which algorithms are used. One candidate is the company's recently introduced Gemini 2.5 Pro large language model, which is particularly adept at application development tasks. It has set a record on the popular LMArena benchmark for measuring LLMs' coding skills. Given that Opal is geared towards creating simple applications, it may not require the advancing programming features offered by Gemini 2.5 Pro. Google may be using a less capable but more power-efficient coding model to power the tool. Opal's clip generation features, in turn, are presumably based on one of the company's Veo video algorithms. Opal is rolling out with more than a half dozen pre-built applications. Some focus on consumer use cases such as designing video games. The rest enable workers to generate marketing materials, research products and perform other business tasks. On launch, Opal is available to users in the U.S. through a public beta program. The tool can be accessed via Google Labs, a webpage that hosts more than two dozen of the search giant's experimental AI products. They automate tasks ranging from searching the web to generating application interface designs.