Google Integrates Opal Mini-App Builder Into Gemini

December 18, 2025
Google has integrated its Opal tool for building AI-powered mini apps directly into the Gemini web app, allowing users to create and customize reusable Gems through a visual editor.

Google has integrated its vibe-coding tool Opal into Gemini by Google, enabling users to create and customize mini applications directly within the Gemini web app. The integration allows users to build their own AI-powered tools, known as Gems, through a visual interface.

The Opal feature is now accessible from the Gems manager in Gemini. Users can describe the app they want to build using natural language, and Gemini will generate it using its AI models. The visual editor displays the steps involved in creating the app, which can be rearranged or linked together without writing code.

A new view in the editor turns user prompts into a step-by-step list, helping users better understand and modify how their mini apps function. For more advanced customization, users can switch to the Advanced Editor at opal.google.com. Once created, these mini apps can be reused within Gemini.

The integration expands Gemini’s customization options, aligning with the growing trend of AI-assisted app creation tools that allow users to build applications through conversational input rather than traditional programming.

We hope you enjoyed this article.

Consider subscribing to one of our newsletters like Daily AI Brief or AI Programming Weekly.

Also, consider following us on social media:

Subscribe to AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more