About CHETI

An innovative AI learning platform from the Chemistry Didactics department at RPTU Kaiserslautern-Landau (Campus: Kaiserslautern).

Our Vision

CHETI combines modern AI technology with subject-didactic expertise. Our goal is to support students with the help of an LLM-based learning tutor and make learning chemistry content more engaging and effective. The AI is adapted to promote self-efficacy in chemistry. At the same time, CHETI is a research platform to further investigate the interaction between LLMs and learners.

AI-Powered Tutors

Through the use of LLMs (Large Language Models) like GPT-4 and Claude, we simulate interactive tutoring systems. These enable adaptive feedback and personalized assistance for complex chemistry questions.

Research Project

This project is part of the research at the Chemistry Didactics department at RPTU in Kaiserslautern. We investigate how AI tools can be effectively and safely integrated into educational scenarios to deepen chemical understanding and support teachers.

RPTU KaiserslauternDepartment of Chemistry

AI Chat Systems: Technical Architecture

How the two chat types of CHETI work — explained in an understandable way.

1

The Two Chat Types at a Glance

Both systems use the same technical infrastructure but differ fundamentally in context and knowledge access.

Learning Material Chat

Topic-based Tutor

The student is in a specific learning module (e.g., "Acids and Bases"). The AI knows the learning content, the tasks, and the student's previous answers. It responds with context and provides targeted support.

Access to Learning MaterialTask ContextTask-specificEmbedded

Free Learning Chat

Untethered Tutor

The student opens a standalone chat page, detached from any specific learning module. They can ask any chemistry questions — e.g., to prepare for an exam or out of interest in a topic.

No Learning MaterialNo TasksOpen TopicsOwn Page
2

How AI Responses Are Generated

The steps a student query goes through from typing to response.

Learning Material Chat

8 Steps

Free Learning Chat

5 Steps

1. Student Message

Security check: no personal data, no injection attempts.

1. Student Message

Identical security check. Images can also be uploaded.

Validation
Validation

2. Assign Session

One chat session per student and lesson. Messages are counted (quota).

2. New Session

Each chat creates its own session. Sidebar for previous chats.

Intent
Intent

3. Classify Intent

Automatic detection: task, explanation, small talk, or off-topic.

3. Classify Intent

Same classification, but "task" is never detected (no context).

RAG

4. Search Learning Material (RAG)

The question is compared with the learning material. The 5 most relevant text passages are selected (vector + full-text search).

No Access to Learning Material

Prompt

5. Compile Context

Tutor rules, learning passages, tasks + answers, chat history.

4. Compile Context

Simplified tutor prompt. Chat history as the only context.

AI
AI

6. Generate Response

AI model generates response as a live stream (token by token).

5. Generate Response

Stream-based output, storage, logging. Without solution protection.

Safety

7. Solution Protection

Automatic comparison with model solution. On violation: restart with stricter prompt.

No Solution Protection Needed

Save
Save

8. Save & Log

Response in DB, all steps logged for quality analysis.

Save & Log

Response in DB, all steps logged for quality analysis.

Core Differences

No RAG Retrieval

No Solution Protection

Simplified Prompt

Targeted search for text passages from the learning content and use as context (Step 4).

Safety guard checks whether the AI reveals the model solution (Step 7).

Tutor rules, learning passages, task context, and didactic modes.

No access to learning material. Only general knowledge of the AI model.

No tasks available, so no solution protection needed.

General chemistry tutor without material-specific instructions.

3

How the AI Accesses Learning Material

The Retrieval-Augmented Generation (RAG) method enables the AI to respond specifically from the learning material.

Step 1

Preparation

Learning material is broken into sections. Each receives a mathematical representation (3,072 dimensions). Images are described by AI.

Technical: 1,250 characters/chunk, pgvector

Step 2

Search

Student question is converted to a vector. Parallel search: semantic similarity + word matching. Results are combined.

Technical: Hybrid Search, RRF, MMR

Step 3

Integration

5 most relevant passages + question + tasks to AI. Formulates technically correct answer. Images also as context.

Technical: Dual-Channel, Token Budget
4

Didactic Control of the AI

How the system ensures the AI acts as a tutor — and not as a solution provider.

Intent Routing

Each message is automatically assigned to a category. The AI responds differently depending on the category:

Task

Help with task → Scaffolding (without solution)

Explanation

Concept question → Explanation mode with learning material

Evaluation

Check solution → Evaluation mode

Small Talk

Greeting, farewell → Short response

Off-Topic

Non-chemistry → Redirect to learning

Solution Protection

Before the AI response is displayed, an automated system checks whether it contains the model solution.

✓ Response Passes Check

Displayed directly. Hints and thought prompts, but not the solution.

⚠ Partial Solution Detected

Second attempt: AI should only state the next thought step.

✗ Complete Solution Leaked

Response is replaced: "I cannot tell you the solution directly."

5

Direct Comparison

The key differences at a glance.

PropertyLearning Material ChatFree Learning Chat
LocationEmbedded in learning pageStandalone page
Knowledge BaseLearning material of the subtopicGeneral AI knowledge
Task ReferenceYes — tasks + student answersNo
Solution ProtectionYes — automatic checkNo
Didactic Modes3: Scaffolding, Explanation, EvaluationGeneral Tutor
Message LimitConfigurable per subtopicUnlimited
Personalization (optional)Self-assessment, Encouragement style, Interests, LearningSelf-assessment, Encouragement style, Interests, Learning
Image UploadYes (if enabled)Yes
SessionsOne per student + subtopicAny number, sidebar
AI ModelPer subtopic / class / globalPer class
Cite (APA 7)

Using CHETI for your research? Find the appropriate citation in APA 7 format here.

Fitting, N., & Seibert, J. (2026). CHETI: AI Tutor for Chemistry. Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau. https://cheti-ki.de/