Proactive Agentic Whiteboards: Enhancing Diagrammatic Learning
An AI-powered whiteboard assistant that proactively completes and refines educational diagrams through multimodal understanding.
Title: Proactive Agentic Whiteboards: Enhancing Diagrammatic Learning
Authors: Suveen Ellawela, Sashenka Gamage, Dinithi Dissanayake
Link: https://arxiv.org/html/2512.01234v2
Educators frequently rely on diagrams to explain complex concepts during lectures, yet creating clear and complete visual representations in real time while simultaneously speaking can be cognitively demanding. Incomplete or unclear diagrams may hinder student comprehension, as learners must mentally reconstruct missing information while following the verbal explanation. Inspired by advances in code completion tools, we introduce DrawDash, an AI-powered whiteboard assistant that proactively completes and refines educational diagrams through multimodal understanding. DrawDash adopts a TAB-completion interaction model: it listens to spoken explanations, detects intent, and dynamically suggests refinements that can be accepted with a single keystroke. We demonstrate DrawDash across four diverse teaching scenarios—spanning topics from computer science and web development to biology. This work represents an early exploration into reducing instructors' cognitive load and improving diagram-based pedagogy through real-time, speech-driven visual assistance, and concludes with a discussion of current limitations and directions for formal classroom evaluation.
DrawDash listens to your spoken explanations while you draw, then suggests improved and completed diagrams that you can accept with a single keystroke (TAB). The system combines speech recognition, visual understanding, and generative AI to enhance diagram-based teaching and learning.
DrawDash consists of two main components: a backend API and a frontend web application. For detailed setup instructions, please refer to:
- Backend Setup: See backend/README.md
- Frontend Setup: See frontend/README.md
If you have any questions or feedback, please feel free to reach out to us at suveen.te1[at]gmail.com.
The software code is licensed under the MIT License.