Home OpenAI announces new ‘deep research’ ChatGPT agent

OpenAI announces new ‘deep research’ ChatGPT agent

OpenAI introduced its deep research agent on Sunday (February 2) with a claim that it accomplishes in tens of minutes what would take a human many hours.

“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,” the technology company said in a blog post announcing the news.

The agent will be powered by a version of the upcoming OpenAI o3 model which will be optimized for web browsing and data analysis. Some of its standout features include reasoning to search, interpret, analyze large amounts of text, images, and PDFs on the internet.

​​https://twitter.com/OpenAI/status/1886219085236850889

The company has described it as marking “a significant step toward our broader goal of developing AGI, which we have long envisioned as capable of producing novel scientific research.”

Named ‘deep research,’ the agent has been designed and built for people who do intensive knowledge work in areas like finance, science, policy, and engineering as it thrives on doing “thorough, precise, and reliable research.”

For those not familiar with those fields, it’s also said to be equally useful for discerning shoppers who are looking for hyper-personalized recommendations on purchases that would usually require a lot of research into them like cars or appliances.

How to use OpenAI’s deep research agent

The ‘deep research’ agent is accessible through OpenAI’s ChatGPT. The name is viewable within the message composer. You can click on the tool and start entering your query there.

To support your question, files or spreadsheets that add context can be added. Unlike the normal ChatGPT which spews out an answer fairly quickly, deep research could take anywhere from 5 to 30 minutes to complete the work.

A notification will be provided to state that research has been completed, with the final output being a report within the chat. Over the next few weeks, OpenAI will add embedded images, data visualizations, and other analytic outputs for additional clarity and context.

Featured Image: Via OpenAI blog

About ReadWrite’s Editorial Process

The ReadWrite Editorial policy involves closely monitoring the gambling and blockchain industries for major developments, new product and brand launches, game releases and other newsworthy events. Editors assign relevant stories to in-house staff writers with expertise in each particular topic area. Before publication, articles go through a rigorous round of editing for accuracy, clarity, and to ensure adherence to ReadWrite's style guidelines.

Sophie Atkinson
Freelance Journalist

Sophie Atkinson is a UK-based journalist and content writer, as well as a founder of a content agency which focuses on storytelling through social media marketing. She kicked off her career with a Print Futures Award which champions young talent working in print, paper and publishing. Heading straight into a regional newsroom, after graduating with a BA (Hons) degree in Journalism, Sophie started by working for Reach PLC. Now, with five years experience in journalism and many more in content marketing, Sophie works as a freelance writer and marketer. Her areas of specialty span a wide range, including technology, business,…