Learning Companion

The modern learning stack

Online first

The Learning Companion is designed as companion for online-centered learning, supporting both synchronous and asynchronous participation, both in-person, mixed, or hybrid learning settings.

Designed for abundance

Learning in the 21st century is not about scarcity, but about abundance. Its not just about slides and lecture notes, but also about whiteboards, recordings, learning videos, and curated content like books, blog entries, or YouTube videos.

Learning experience

Design learning experience is about creating opportunities for learners to engage with the content, not about managing learning. The companion supports integrating materials for exploration, preparation, repetition, and reflection. It supports timeline-based, topic-based, structure-based, and conversational access to all the materials. Views can be embedded, e.g., into whiteboards.

AI enhanced

Based on the content of the supplied materials, ranging from transcripts to web resources, a GPT-based chatbot will be able to answer questions and provide additional information. Comprehensive observability and self-evaluation capabilities simplify continuous improvement.

Lightweight and efficient

Using a headless CMS and preferring convention over configuration, the Learning Companion is designed to be lightweight and efficient for the teacher. Many aspects, including the chatbot interface, can be easily fine-tuned to achieve the best possible learning experience.

Cloud native

The Learning Companion is designed to be cloud-native, using scalable object storage for all the materials, stateless container(s) for the backend functionality with easy loadbalancing.

Course model

The Learning Companion uses a flexible model with feature flags. It supports

A timeline-based view on course slots with concrete dates, and allows for associating directly with the slot (like recordings or boards), or indirectly via course sections.
A topic-based view on all the provided materials and course slots.
A structural view putting the whole course into a more traditional table of contents
Conversational view using a state-of-the-art LLM-based chatbot

Content management

Easy to use admin backend
Extensive use of convention over configuration to reduce the
Flexible and extensible use of scalable object storage as a native store

Chatbot features

Based on GPT-4o as a standard model, the model to be used can be configured (for each of the courses of components separately)
Querying indexed documents (with metadata), implementing a RAG approach with per-course configuration of major parameters (like number of chunks)
Configurable history management
Generate topic suggestions
Generate follow-up question suggestions
Inline citations of the used materials for better traceability (with direct quotes)
Multiple and configurable (in CMS) prompts chosen at runtime (dynamic prompt selection) (either via LLM or direct similarity search)
Sidebar with suggested course materials relevant to the question
Thumbs voting to improve the quality
Extensive chatbot interaction logging and self-evaluation via LLM-as-a-judge
Generate clarifying info prompts to the user
Specialized tools (or functions) using an agentic workflow to make the LLM automatically choose what to include - especially useful for API-based integration of content.
Supports advanced UML model generation via PlantUML rendering and specialized prompts
Low-barrier improvement via directly supported Q&A

Flexible document indexing

Wide range of documents such as pdf, md, docx, pptx, but also video transcripts (both vtt and YouTube)
Periodic indexing of web sites and other content
Observability of workflow execution
Multiple indexing methods, including multimodal indexing
Configurable indexing parameters, such as chunking strategy
Easy reindexing and chunk inspection from the CMS

Evaluation and quality monitoring

Anonymous logging
Self evaluation using LLM-as-a-judge approaches
Manual quality tagging and annotation for improvement
Auto-expiring information (e.g., semester-related)

Extensible and customizable

Many feature flags, supporting, e.g., synchronous courses (with timeline), asynchronous courses, or course-indepenten bots
Themeable, supporting automatic and manual switching between light and dark mode
Easy addition of new material types
Supports multiple languages (or a course level)
Models, prompts, and chatbot parameters directly configurable in CMS
Extensive API and views designed to be embedded into other sites (fragments and OEmbed)
Planned: compose chatbots from multiple courses or more specialized bots

Modern technologies

FastAPI with Jinja2 (with JinjaX components) and extensive use of Pydantic
Hypermedia-first approach using HTMX
Reactive web design
Built ontop of langchain
Prefect as orchestrator for indexing tasks
Pinecone Serverless as vector database
MongoDB Atlas for history management
Log observability with Pydantic's LogFire, GenAI observability with LangFuse