OpenAI has just announced a new AI agent that can synthesize large amounts of information online to complete multi-step research projects.
“Deep research is OpenAI’s next agent that can do work for you independently—you give it a prompt, and ChatGPT will find, analyze, and synthesize hundreds of online sources to create a comprehensive report at the level of a research analyst,” OpenAI wrote in a blog post.
According to the company, deep research is powered by a version of the o3 model optimized for browsing the web and analyzing data. It utilizes reasoning capabilities to search, interpret, and analyze text, images, and PDFs found on the internet. The agent can also change course as it reacts to the information it finds.
Each of its outputs is fully documented with citations and a summary of how the AI came to its conclusion, which allows the user to easily verify the results.
It can take between 5 to 30 minutes to complete research, depending on the complexity of the request, and users will receive a notification when it’s complete.
“It is particularly effective at finding niche, non-intuitive information that would require browsing numerous websites. Deep research frees up valuable time by allowing you to offload and expedite complex, time-intensive web research with just one query,” OpenAI wrote.
Deep research is currently only available to Pro users, but it will be expanded to Plus and Team users at some point, followed by Enterprise. Users are limited to up to 100 queries per month at the moment.
The company also plans on adding embedded images, data visualization, and other analytics outputs in deep research reports in the coming weeks.
More information about deep research is available here.