Writing & Notes
Field notes on building
trustworthy analytics agents
Thoughts on metrics, evaluation, failure modes, and what it actually takes to trust an AI with business data.
May 12, 2024
Failure Modes
The 10 ways my agent got revenue wrong
Wrong denominators, join multiplication, and more subtle SQL generation errors.
Read note →
May 6, 2024
Evaluation
Version 2 results: better SQL, same reasoning gaps
Adding metric definitions helped—but root cause analysis is still weak.
Read note →
Apr 28, 2024
Methodology
Building my golden question set
Why I weight questions by business risk, not just semantic accuracy.
Read note →