A SciPy 2026 talk on Canvas Chat, a browser-based tool for non-linear, visual AI-assisted data analysis with Python and LLMs.
Talk recorded at SciPy 2026 on Canvas Chat, a browser-based tool that combines Python's data science stack with LLM connectivity for natural language interaction with data. Built on Pyodide, it runs entirely in the browser with no server-side computation required; you bring your own API keys for LLM access, while all session data persists locally in IndexedDB. The visual, non-linear interface represents conversations as nodes on an infinite canvas, supporting branching, merging, and stateful exploration of data analysis workflows. The talk shows how browser-based Python plus LLMs can democratize data science by removing infrastructure barriers while preserving privacy and reproducibility.