heyprof

Course and Session Management

Instructors create courses in the dashboard and receive an eight-digit access code. Each course is divided into sessions corresponding to individual lecture dates. The order of all elements can be adjusted via drag-and-drop.

Material Management and Annotation

Uploaded PDF slides can be annotated using a freehand drawing tool. Students see these annotations as an overlay. After upload, materials are ingested: text is extracted, split into sections, embedded and stored in the vector store, enabling the AI tutor to retrieve relevant passages from the course script on demand.

Task Editor

The editor supports three types: Free text, Multiple choice and Code (Python). For each task, the instructor can store a model solution, private tutor instructions and labels and collections. Tasks can be imported from LaTeX source files. Cover images are generated automatically via DALL-E 3.

Exam Management

Exams consist of numbered questions with a score and countdown timer. Questions can be imported from scanned PDF exam sheets — an AI pipeline automatically extracts texts, numbering and points. After the exam, all submissions are available with AI-generated assessments.

Recordings and Transcription

A browser-based audio recorder enables direct recording of lectures. Whisper v2 transcribes the recording in the background. GPT-4o then generates a structured summary — visible to all students.

AI Configuration

At course level, tutor instructions can be stored for material and task questions, and the tutor can be deactivated entirely. The tutor's personality (referred to as "Soul" in the system) is configurable via Markdown files — tone, teaching style and focus areas.

Dashboard and Learning Studio

The dashboard shows enrolled courses with a progress indicator. The Learning Studio lists all sessions chronologically — with PDF viewer, annotation overlay, lecture recording with transcript and summary, and the session's tasks all on one page. In the PDF viewer, students can highlight a passage; the AI tutor receives this excerpt as a focus hint.

Tasks — Six Submission Channels

• Text/Code — direct input with instant AI assessment
• Drawing canvas — freehand solution for mathematical or diagrammatic answers
• QR photo — smartphone scans QR code, takes a photo, answer appears on the desktop
• AI tutor — immediate Socratic support in the integrated chat
• Practice variant — AI generates a structurally identical task with different numbers or function names
• Show solution — after a genuine attempt

Retrieval-Augmented Generation (RAG)

Before the AI tutor responds, its system prompt is enriched with the complete task text, private tutor instructions, the student's current Python code, semantically retrieved passages from the course materials and the instructor's handwritten annotations. When a student asks "What is a linked list?", the system searches the most relevant sections from the course script — not from the model's general world knowledge — and forces the tutor to respond using exactly the concepts and notation of the lecture.

Socratic Mode and Explanation Mode

In Socratic mode, the tutor asks only counter-questions that move the student one step forward without revealing the solution. In explanation mode, the tutor explains directly, actively and vividly — with concrete examples and everyday metaphors, referencing the provided slide content.

Automatic Assessment

Text responses are assessed through a structured GPT-4o call. Handwritten or photographed solutions are analysed by the vision model, checked for relevance and converted to LaTeX notation. The assessment immediately updates the progress indicator.