Turns out "Claude Code over files in S3" quickly becomes "rebuild half the data warehouse stack" 🫠 Schemas, datasets, lineage, file refs, etc. OpenAI's Data Agent post made us feel slightly less insane 😄 Read more: datachain.ai/blog/openai-da…

@FullStackML Exactly. The hard part is not “code over S3 files.” It is giving the agent enough data context: schemas, lineage, permissions, refs, and recovery. That’s where the real complexity starts.

@APRiCiTY1314520 Yeah 😄”Read files from S3” is the hello world. The real fun starts when the agent forgets where the files came from, what schema they had, who can access them, and whether yesterday’s output was wrong.