Essays
PromptQL's writing on shared context, accuracy, and building enterprise AI you can actually trust.
The semantic layer is dead. Long live the wiki.
Most “AI on data” programs are just semantic-layer maximalism with a new paint job. A Wikipedia-style model is a better way to think about organizational meaning — and to make AI reason accurately.
Read essay→
Being "Confidently Wrong" is holding AI back
The failure mode that stalls “AI for data” efforts or "AI on my APIs" efforts isn’t psychedelic hallucination—it’s confident inaccuracy: plausible answers that are wrong in subtle and costly ways.
Read essay→
43% accuracy with Opus-4.6 & friends - will Text-to-SQL ever be good enough?
The Data Agent Benchmark from UC Berkeley’s EPIC lab shows frontier models top out around 43% on real-world data questions — and what that means for text-to-SQL on enterprise data.
Read essay→3 Silent Killers of Enterprise AI (And Why Your Pilot Will Probably Fail)
Smart teams spin up an AI project, the demo looks great — then nothing happens. The three quiet failure modes that stall enterprise AI pilots, and how to get past them.
Read essay→