Thesis Proposal - AI Chatbot for Onboarding and Project Document Assistance

Background

Onboarding new employees and providing access to project documentation can be time-consuming and inefficient. Conversational AI offers a way to improve knowledge accessibility by guiding employees through onboarding materials and project resources.

This thesis focuses on designing an AI powered chatbot that leverages open-source Large Language Models (LLMs) combined with Retrieval Augmented Generation (RAG) to provide accurate, context-aware guidance. The system will help employees to understand company policies, guides, and onboarding materials and access project-specific documents, meeting notes, diagrams, and repository links. By combining conversational AI with intelligent document retrieval, the system aims to reduce the time employees spend searching for information and improve onboarding efficiency.

Work description

• Gather onboarding materials, company policies, guides, and project documentation.
• Index and structure documents for RAG based retrieval with secure access controls.
• Implement the AI chatbot using an LLM integrated with RAG for knowledge retrieval.
• Develop conversational flows for onboarding and project-related queries.
• Integrate with enterprise knowledge sources such as SharePoint, Confluence, Notion, or internal drives.
• Measure the chatbot’s accuracy in retrieving relevant documents.
• Assess usability, response relevance, and efficiency improvements in accessing onboarding and project information.

We think the thesis will contain the following parts,

• Literature review on LLMs and RAG for knowledge retrieval.
• Design of data ingestion, indexing, and retrieval pipelines.
• Implementation of the chatbot and enterprise integration.
• Evaluation methodology and analysis of results.

Qualifications

• Programming experience in Python.
• Interest in AI, knowledge retrieval, and enterprise systems.
• Background in Computer Science, Data Science, AI, or equivalent.
• Meritorious: Familiarity with LLMs, RAG, document indexing, and enterprise integration.
• Good knowledge in both Swedish and English. 

To give you the best possible support during your thesis, we’d like you to be able to come to the office connected to the project and spend most of your time working from there.

Application:

We look forward to receiving your resume, and preferably, a personal letter in which you explain why you want to write your thesis with Syntronic.

We screen and evaluate applications on an ongoing basis. The thesis project may be filled before the application deadline.

Ansök här