CLAPP: The CLASS LLM Agent for Pair Programming
This work addresses a domain-specific problem for computational cosmologists by providing a tool to enhance productivity in human-AI collaboration, though it is incremental as it applies existing methods to a new application area.
The authors tackled the problem of supporting researchers using the CLASS cosmology code by developing CLAPP, an interactive AI assistant that provides conversational coding support, resulting in a deployed web application that lowers the entry barrier for scientists unfamiliar with AI tools.
We introduce CLAPP (CLASS LLM Agent for Pair Programming), an interactive AI assistant designed to support researchers working with the Einstein-Boltzmann solver CLASS. CLAPP leverages large language models (LLMs) and domain-specific retrieval to provide conversational coding support for CLASS-answering questions, generating code, debugging errors, and producing plots. Its architecture combines multi-agent LLM orchestration, semantic search across CLASS documentation, and a live Python execution environment. Deployed as a user-friendly web application, CLAPP lowers the entry barrier for scientists unfamiliar with AI tools and enables more productive human-AI collaboration in computational and numerical cosmology. The app is available at https://classclapp.streamlit.app