ChatGPT Deep Research now runs on GPT-5.2 with source controls and real-time tracking

ChatGPT Deep Research Now Lets You Pick Sources, Adds Built-In Documents

(Credit: Algi Febri Sugita/SOPA Images/LightRocket via Getty Images) Deep Research in ChatGPT is designed to produce in-depth, highly researched reports by pulling information from multiple sources into a single place. A series of new upgrades now makes it "more accurate" than ever before, according to OpenAI. The big change is a switch to its latest GPT 5.2 model to power Deep Research. You can now view the reports you generate directly in ChatGPT, without downloading a separate file to read them. A table of contents sits on the left-hand side of each report, while the right-hand shows a list of the sources so you can jump to more information. You can then download the file if you're happy, with options for Markdown, PDF, or Word files. Other upgrades include the ability to specify which sites Deep Research will use for each report. The new feature lets you add multiple relevant sources for ChatGPT to consider, or you can select an additional option to ask it to prioritize those sources while allowing further online searches. You can also add specific apps to your report runs. OpenAI's example shows a plug-in for financial markets from the London Stock Exchange Group (LSEG) in use for more specialized results. You can also monitor each report in real time. Deep Research tasks can sometimes take up to 30 minutes, and now you can view how they're going or request edits to them as they're happening. For example, you can ask it to add new sources or queries midway through a report, rather than having to rerun the entire report after it's complete to introduce extra information. If you subscribe to ChatGPT Plus or Pro, you'll be able to access the features now as they first rolled out on Feb. 10. The same features will come to other users in the "coming days," with no clear launch date set for free users or those on a ChatGPT Go plan. Disclosure: Ziff Davis, PCMag's parent company, filed a lawsuit against OpenAI in April 2025, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.

Deep Research in ChatGPT Is Getting These New Features

OpenAI is adding a full-screen viewer with index and citations in margin OpenAI updated the Deep Research tool in ChatGPT this week. The agentic research assistant was first introduced by the San Francisco-based artificial intelligence (AI) giant in February 2025, and it was designed to help users conduct multi-step research on complex topics. Now, one year later, the company has added more controls and a new full-screen report viewer to the tool, allowing users more flexibility in both creating the research document and viewing it. Notably, the company has also updated the GPT-5.2 Instant AI model. Deep Research in ChatGPT Gets New Features In its release notes for ChatGPT, the AI giant announced and detailed the new capabilities in Deep Research. The improvements can be divided into two groups: the first focusing on the new controls, and the second on the viewing experience. In the first group, OpenAI has now added an option to let users narrow the focus of research to specific websites. This was a highly requested feature because, so far, the only way Deep Research could be grounded was by specifying the website limiters in the prompt itself. However, the ability to add this information into the tool at a system level will let users see more accurate and focused responses. Additionally, users can also enable connected apps while conducting research and use them as trusted sources. Apart from this, users can also edit a research plan before it begins. This is particularly useful given that earlier users could only redirect the research after it started. If a user wanted to alter details before the plan was created, they would have to start all over again. The ability to adjust the direction of the research mid-run continues to be available. Coming to the second group of improvements, Deep Research now has a redesigned sidebar entry point and a full-screen report viewer. The latter opens in a document viewer-like interface, complete with side panels for index (on the left) and citations (on the right). The index is also interactive, and users can click on any heading or subheading to quickly reach that part. Separately, the AI firm has also updated the GPT-5.2 Instant model in ChatGPT and application programming interface (API). OpenAI says the responses are now "more measured and grounded" in tone, which makes them contextually appropriate to the conversation. Further, the updated model also provides clearer output and more relevant answers to how-to questions and advice.

ChatGPT Deep Research Now Runs on GPT-5.2

What if your research assistant could not only sift through mountains of data but also deliver precise, citation-backed insights in real time? That's exactly what GPT-5.2 brings to ChatGPT Deep Research, and is now being rolled out by OpenAI. It doesn't just answer questions, it reshapes how professionals approach deep research, offering unparalleled accuracy and the ability to integrate trusted, verified sources directly into your workflow. Imagine synthesizing complex technical documents or comparing regulatory frameworks across jurisdictions, all while maintaining full oversight and control of the process. With GPT-5.2, that vision is now a reality. In this overview, we'll explore how GPT-5.2 is redefining ChatGPT Deep Research with real-time tracking, customizable data integration, and enterprise-grade security. You'll discover how it seamlessly connects to proprietary datasets, generates structured overviews in minutes, and ensures every insight is backed by credible references. Whether you're navigating intricate market trends or tackling compliance-heavy industries, GPT-5.2 offers a dynamic, efficient approach to solving complex challenges. By the end, you might just rethink what's possible when AI meets professional research. The release of GPT-5.2 has introduced a new era in how ChatGPT manages deep research, offering faster, more precise, and citation-supported results. By integrating access to verified sources and allowing real-time tracking, this upgrade enables you to address complex queries with unparalleled accuracy and efficiency. Designed with professionals in mind, GPT-5.2 provides structured overviewing, customizable data integration, and enterprise-grade security, making it an essential tool across a wide range of industries. GPT-5.2 redefines the research process by seamlessly integrating with trusted and authenticated sources. This ensures that your findings are grounded in reliable data, allowing you to: Whether you're analyzing market trends, comparing scientific studies, or reviewing regulatory frameworks, GPT-5.2 ensures your research is both accurate and verifiable. For example, when synthesizing technical documents or evaluating industry-specific regulations, the model provides results that are not only precise but also supported by credible references. Learn more about ChatGPT by reading our previous articles, guides and features : The real-time tracking feature of GPT-5.2 offers complete oversight of your research process. This functionality allows you to monitor progress, adjust focus, or introduce new sources as your objectives evolve. Such dynamic flexibility ensures that your research remains aligned with your specific goals. Structured overviews can be generated in as little as 30 minutes, significantly reducing the time required for complex tasks. For instance, if you're analyzing a lengthy technical document, you can pause the process to refine priorities or incorporate additional data sources. This ensures that the final output is tailored to meet your exact requirements, saving time while maintaining quality. GPT-5.2 is equipped to handle even the most intricate research challenges with ease. Its long-context reasoning capabilities allow you to: By reducing latency and enhancing the quality of its outputs, GPT-5.2 ensures that even the most demanding queries are addressed efficiently. For example, when comparing findings from multiple scientific studies, the model can identify discrepancies, highlight key insights, and provide a comprehensive analysis. This level of detail and accuracy makes it an invaluable tool for professionals working in research-intensive fields. For organizations, GPT-5.2 introduces enterprise-grade permissions to ensure strict control over data and access. Administrators can: This feature is particularly critical for industries with stringent compliance requirements, such as healthcare, finance, or legal services. By maintaining control over the tools and sources used in the research process, GPT-5.2 ensures that your organization adheres to the highest standards of data security and integrity. One of the standout features of GPT-5.2 is its ability to customize source integration, allowing you to prioritize high-quality, reliable data. You can: For example, if your organization relies on proprietary data, GPT-5.2 enables seamless integration of these datasets into your research workflow. This ensures that your findings are not only accurate but also tailored to your specific needs, avoiding reliance on general web results that may lack credibility. Once your research is complete, GPT-5.2 simplifies the process of sharing and refining your findings. Overviews can be downloaded in PDF or DOCX formats, making them easy to distribute across teams or stakeholders. Additionally, you can refine these overviews directly within the chat interface, allowing quick updates or expansions as needed. This feature is particularly valuable for collaborative projects, where multiple contributors may need to review and enhance the final output. By streamlining the sharing and refinement process, GPT-5.2 ensures that your research remains both actionable and adaptable to changing requirements. GPT-5.2 is tailored for professionals who require credible, actionable insights. By using authenticated sources and approved tools, it ensures that your research meets the highest standards of reliability. Whether you're conducting regulatory reviews, analyzing market dynamics, or synthesizing scientific data, GPT-5.2 equips you with the tools to achieve your objectives efficiently and effectively. Its combination of real-time control, customizable integration, and enterprise-grade security makes GPT-5.2 an indispensable resource for professionals across industries. By addressing complex queries with precision and delivering structured, citation-backed overviews, GPT-5.2 sets a new benchmark for AI-driven research capabilities in ChatGPT. Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.