The Data Exchange

Coding Agents Meet Data Science

In this episode, host and guest Mikio Braun discuss the emerging role of coding agents—AI tools that generate code—in data science workflows. They explore how these agents excel at writing code but often lack the skepticism and domain awareness needed for robust data analysis, highlighting challenges like data quality, model validation, and context awareness. Braun points to emerging solutions such as structured-data foundation models (e.g., Kumo) and context file systems (e.g., Chetan Konki's upcoming ROTE) that aim to make AI more data‑science‑savvy. The conversation also touches on the team‑level impact of coding agents, noting that increased individual productivity will shift bottlenecks to code review and require new coordination processes.