New Perplexity Labs Feature Turns Prompts into Reports, Apps, and More

The AI search engine startup Perplexity AI introduced “Labs,” a new feature that transforms user prompts into fully developed projects. The feature is available starting Friday for Pro subscribers on the web, iOS, and Android.

Labs builds on the platform’s earlier capabilities, such as its fast-answer “Search” and in-depth “Deep Research” tools.

While those modes focus on retrieving and analysing information, Labs acts more like a virtual project team, one that can produce reports, dashboards, web apps, and more, often within 10 minutes.

It can be understood as an extended version of the original Deep Research feature, with the ability to make things out of the research.

“Using Labs is like having a team,” the company said in the blog post. 

“Labs can craft everything from reports and spreadsheets to dashboards and simple web apps — all backed by extensive research and analysis.”

The system uses tools like web browsing, code execution, and asset generation—including charts, images, and spreadsheets—to create structured outputs from scratch.

Each Lab includes an “Assets” tab to organise all generated content and an “App” tab to build interactive web elements such as dashboards and slideshows. Unlike Deep Research, which typically wraps up in minutes, Labs is designed for extended workflows and richer outputs.

The company also said it is renaming “Deep Research” to simply “Research,” positioning it as a middle ground between Search and Labs.

To help users get started, Perplexity has featured a Projects Gallery of examples. Labs is accessible via the mode selector in the input bar across supported platforms, with desktop app support coming soon.

Recently, Perplexity has rolled out Comet, its agentic web browser, as a beta version, limited to select Apple Silicon Mac users for now. Selected testers received early access to the browser, and the company encouraged feedback on bugs and features as development continued. The browser aims to reimagine web browsing through context-aware intelligence. Comet personalises responses based on a user’s browsing history and open tabs, all stored locally and not used for model training.