• cybersecurity
• LLM
• RAG
• Rust
• secure code

Software engineering methodologies are rapidly evolving as new technologies and tools emerge to enhance code quality. This thesis explores the design and development of a Retrieval-Augmented Generation (RAG) chatbot intended to help developers with methods and tools to organize and structure robust and secure Rust code. The Rust programming language is recognized for its memory safety and performance and is experiencing a rise in popularity. The proposed chatbot enhances conventional Large Language Model capabilities by retrieving and incorporating knowledge from external sources. This study reviews Rust secure coding guidelines and existing RAG methodologies, proposes a comprehensive architecture for a Rust Development Assistant, and evaluates the effectiveness of the assistant.