ChatGPT launches study mode to boost learning through guidance

ChatGPT has launched a new study mode designed to provide step-by-step guidance for learners rather than simply offering answers to questions.

The new feature is now available to all logged-in users on the Free, Plus, Pro, and Team plans, with ChatGPT Edu to gain access in the coming weeks. Study mode seeks to address growing use of ChatGPT as an educational tool and concerns among educators regarding its impact on the quality of learning.

Rather than directly supplying solutions, study mode delivers a sequence of guiding questions tailored to both the student’s learning objectives and skill level. The intention is to encourage deeper engagement with material and help users build genuine understanding, not just complete tasks.

Development approach

The development of study mode was informed by collaboration with teachers, scientists, and experts in pedagogy. According to the announcement, these custom system instructions focus on behaviour that research links to deeper learning. This includes encouraging active participation, managing cognitive load, promoting self-reflection and metacognition, fostering curiosity, and providing actionable feedback.

“Instead of doing the work for them, study mode encourages students to think critically about their learning. Features like these are a positive step toward effective AI use for learning. Even in the AI era, the best learning still happens when students are excited about and actively engaging with the lesson material.” – Robbie Torney, Senior Director of AI Programs at Common Sense Media.

Study mode was created in response to both the popularity of ChatGPT as a study aid and to instructor concerns that ease of access to answers could undermine real learning outcomes. According to developers, its design aims to support retention, promote conceptual understanding, and nurture student skills over time.

Key features

Among the principal features of study mode are:

• Interactive prompts: By combining Socratic questioning, hints, and self-reflection prompts, the tool guides students through problems while promoting active learning.
• Scaffolded responses: Information is delivered in a structured way, with key connections between topics highlighted to reduce cognitive overload, especially for complex subjects.
• Personalised support: Lessons are adapted to each user’s ability, with the system assessing skill levels and prior knowledge from previous interactions.
• Knowledge checks: Quizzes and open-ended questions paired with personalised feedback help users track progress and understand material more effectively.
• Flexibility: Users have control over their learning journey and can toggle study mode on or off at any point in a conversation.

Feedback from users

Students involved in early testing have shared their experiences, highlighting both the accessibility and depth the feature offers.

“The best way I’d describe it is a live, 24/7, all-knowing ‘office hours.'” – Noah Campbell, college student

“Study mode did a great job breaking down dense material into clear, well-paced explanations.” – Caleb Masi, college student

“I put study mode to the test to tutor me on a concept I have attempted to learn many times before: sinusoidal positional encodings. It was like a tutor who doesn’t get tired of my questions. After a 3-hour working session, I finally understood it well enough to feel confident.” – Maggie Wang, college student

The ChatGPT development team has cited examples of students using study mode for subjects ranging from Game Theory and Accounting to Discrete Mathematics. The platform now offers structured lesson plans, interactive examples, and staged explanations tailored to diverse learning needs and goals.

How it works

Study mode is activated by selecting the “Study and learn” tool in ChatGPT. Users can engage with the tool for various purposes, including homework help, exam preparation, and learning new topics.

Students can work through problems interactively, receive stepwise feedback, and revisit material as needed. The mode structures complex topics into manageable segments, blending teaching with ongoing assessment.

Future directions

While the current version of study mode is powered by custom system instructions, developers note that this is an initial step. The approach is intended to facilitate rapid iteration based on user feedback, although it may result in some inconsistencies across conversations in the short term.

Research and development efforts continue, with plans to directly train these behaviours into AI models as lessons are learned from ongoing user engagement. Future updates under consideration include clearer visualisations for complex ideas, enhanced goal-setting and progress tracking, and deeper personalisation based on student needs.

The team is also working with academic partners to support research into AI’s impact on education and how such tools can influence learning outcomes. Insights gained from these collaborations are expected to inform future updates and best practices in AI-supported learning.