Blog
Field notes on the messy edges of LLM-assisted analytics. Subscribe via RSS.
- May 22, 2026 #privacy#pii#trust
What 'privacy' means when your copilot sees your warehouse
Privacy in AI data tools is often marketing language. An honest account of the threat model, what l0l1 does at each boundary, and what it doesn't claim.
- May 1, 2026 #validation#architecture
Validation as a first-class layer in AI data tools
If LLMs are going to draft SQL, validation has to stop being a UI warning and become an architectural surface. How we think about it inside l0l1.
- Apr 12, 2026 #validation#llm#sql
LLM-generated SQL is mostly correct — that's the problem
Why 'looks right and runs' is the most dangerous failure mode for AI-generated SQL, and what a validation layer must catch before the dashboard updates.