ChatGPT Launches Deep Research Feature, Can Do Complex Research

ChatGPT present Deep Research (photo: dock. YouTube OpenAI)

JAKARTA After Gemini, OpenAI is now launching the Deep Research feature for the ChatGPT Artificial Intelligence (AI) application. This feature is designed to conduct multi-step research on the internet on complicated tasks.

Deep Research is designed to support a heavy workload and can work independently. If humans need hours to do complex research, ChatGPT can complete it within tens of minutes thanks to the feature.

"You give him an order and ChatGPT will find, analyze and synthesize hundreds of online sources to make comprehensive reports at the research analyst level," OpenAI said on Sunday, February 2.

Deep Research is supported by an optimized AI o3 model specifically for web browsing and data analysis. ChatGPT users can analyze data from plain text, images, to PDF using Deep Research.

How To Use Deep Research

To use this feature, ChatGPT users only need to select the Deep Research option in the messaging part. After that, input the desired question and insert an image or file if the asked question or command is in it.

Give clear prompts and details so that ChatGPT, especially Deep Research, can provide the right results. If so, the sidebar will display a summary of the steps taken as well as the sources used. Usually, this feature works from 5 to 30 minutes.

While waiting, users can focus on activities or other tasks. ChatGPT will show notifications when the research results are complete. The current final results are only in the form of reports in the chat. In the future, OpenAI will add additional media such as embedded images, visualization of data, and others.