heyprof

Course and Session Management

Teachers create courses in the dashboard — either from scratch or from a template course — and receive an eight-digit access code. Each course is divided into sessions. The order of all elements can be adjusted via drag-and-drop.

Course Modules

Features such as exercises, playground, challenges, action weeks and read-aloud can be enabled individually per course. Available modules depend on the education sector of the course.

Material Management

Supports PDF, Word, text and HTML. Uploaded materials can be annotated. PDFs are automatically converted to responsive HTML (AI-powered, two-pass). After upload, materials are ingested: text is extracted, split into sections, embedded and stored in the vector store.

Task Editor

Three task types: free text, multiple choice and code (Python or SQL). For each task: model solution, private tutor instructions, labels and collections. Tasks can be imported from LaTeX. Cover images are generated automatically via DALL-E 3. AI-powered task collections can be generated from course materials.

Exam Management

Exams consist of numbered questions with scores and countdown timers. Questions can be imported from scanned PDF exam sheets via an AI pipeline. All submissions are available with AI-generated assessments.

Recordings and Transcription

Lessons are recorded in-browser and transcribed via Whisper. GPT-4o generates a structured summary — visible to all learners and part of the RAG context.

AI Configuration and Tutor Personalities

At course level, tutor instructions can be set for material and task questions. The tutor's personality is selectable: witty-clear (dry, direct), neutral (factual), metaphorical (vivid with analogies) or colloquial (informal, approachable).

Gamification

Weekly challenges with a raffle system and action weeks with a points system motivate regular participation. Teachers configure criteria, rewards and timeframes.

Dashboard and Learning Studio

The dashboard shows enrolled courses with progress indicators. The Learning Studio combines all session content on one page: materials with PDF or HTML viewer, annotation overlay, lesson recording with transcript and summary, and the session's tasks.

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
• Show solution — after a genuine attempt

Python and SQL Playground

Interactive coding environments directly in the browser: Python with CodeMirror editor and SQL with SQLite databases. The AI tutor knows the current code and database schema and can provide targeted help.

Community

Integrated forum for questions, feature requests and discussions with voting system and status tracking.

Retrieval-Augmented Generation (RAG)

Before the AI tutor responds, its system prompt is enriched with the complete task text, private tutor instructions, the learner's current code, semantically retrieved passages from the course materials and the teacher's handwritten annotations. The AI responds using the concepts and notation of the course — not from the model's general world knowledge.

Socratic Mode and Explanation Mode

In Socratic mode, the tutor asks only counter-questions that move the learner 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 materials.

Automatic Assessment

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