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 RIP $snow

@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.

@FullStackML You didn’t mention .md files

@FullStackML I learned this lesson with Claude 3.7 on windsurf, I don’t know wtf I was thinking