AI Enabled Automated Student Q&A Tool: Prof Notes AI
Bibliographic record
Abstract
Engineering students often face delays in getting their questions answered, whether technical or syllabus-related, as professors are occupied with extensive academic and administrative tasks. This leads to gaps in understanding and a lack of immediate support. Students prefer answers to their questions to be linked to their professor’s notes rather than navigating through excess information, which hinders self-directed learning and the effective use of visual aids. Core engineering and science courses, or any other course that can be deterministic in nature, are well-suited for automated-learning tools that deliver precise answers, unlike open-ended design courses which may have multiple possible answers. This work explores whether an AI-driven tool, with content based on professors’ notes and course outlines, can improve students' learning outcomes by providing immediate and relevant answers. The system, Prof-Notes AI, is a full-stack application that categorizes student queries as either technical or syllabus-related and fetches relevant content, including equations, illustrations, and videos. The frontend, developed using React and JavaScript, provides a user-friendly interface, while the Python-based backend integrates AI frameworks such as GPT models, Llama, and Pinecone vector databases to retrieve contextually relevant information. The system leverages Google App Engine and Firebase for real-time data flow, and a caching system is used to optimize performance and reduce AI computational costs. Security measures, including authentication and data encryption, ensure user data protection. User testing demonstrated that linking answers directly to professor notes significantly improved response relevance compared to generic resources. While many students found Prof-Notes AI a reliable study tool, feedback highlighted challenges in handling complex queries and barriers to adoption due to reliance on alternative resources. However, students appreciated the seamless experience across devices, including mobile phones and laptops. Future updates will focus on enhancing active learning, allowing students to engage in interactive discussions with the AI model. A targeted marketing strategy is essential to raise awareness and integrate the tool into students’ learning routines, positioning Prof-Notes AI as a fundamental resource for self-directed learning in engineering education.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.054 | 0.026 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".