Search and Filter

Learn Like Feynman: Developing and Testing an AI-Driven Feynman Bot

Date

AI Overview

Why it matters

Self-regulated learners often lack the peer or instructor support needed for active learning techniques, while existing educational tools primarily focus on memorization rather than conversational teaching that stimulates deeper comprehension.

Study at a glance
  • Question: Does using an AI-driven conversational bot improve learners' knowledge gains and comfort compared to passive studying?
  • Setting and data: Controlled remote experiment over three days with 14 working adults aged 21–29 enrolled in an online Harvard Justice course.
  • Method: Randomized controlled experiment comparing bot discussions to passive review, using pre- and post-assessments and a self-efficacy survey.
  • AI tools: Feynman Bot, Quizbot.ai
Key findings
  • Learners using the Feynman Bot achieved higher mean learning gains (3.83 points) than passive learners (2.17 points), with more consistent improvement across participants.
  • All bot users reported increased comfort discussing course material with peers, and over 80% preferred the bot over traditional passive study techniques.
  • Participants preferred typing over speech input when interacting with the bot because typing allowed better thought articulation across diverse physical environments.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

The Feynman learning technique is an active learning strategy that helps learners simplify complex information through student-led teaching and discussion. In this paper, we present the development and usability testing of the Feynman Bot, which uses the Feynman technique to assist self-regulated learners who lack peer or instructor support. The Bot embodies the Feynman learning technique by encouraging learners to discuss their lecture material in a question-answer-driven discussion format. The Feynman Bot was developed using a large language model with Langchain in a Retrieval-Augmented-Generation framework to leverage the reasoning capability required to generate effective discussion-oriented questions. To test the Feynman bot, a controlled experiment was conducted over three days with fourteen participants. Formative and summative assessments were conducted, followed by a self-efficacy survey. We found that participants who used the Feynman Bot experienced higher learning gains than the Passive Learners' group. Moreover, Feynman Bot Learners' had a higher level of comfort with the subject after using the bot. We also found typing to be the preferred input modality method over speech, when interacting with the bot. The high learning gains and improved confidence with study material brought about by the Feynman Bot makes it a promising tool for self-regulated learners.