Engineering, strategy, and operational lessons from the work we ship. Opinionated and specific. No "AI is transforming everything" intros.
Most agent demos run for 30 seconds in a sandbox. Production agents have to work for years. Four patterns that hold up.
Most teams treat RAG as plumbing. It isn't. The failure modes live in places that never show up in a demo.
Without evals you can't deploy with confidence, can't improve with discipline, can't catch the regression that's about to embarrass you.
The interesting AI initiatives are never trivially "buy" or "build." They're the ones in between.
Wrong problem, wrong data, wrong adoption, wrong governance. Spotting them early is the difference between deployed and shelved.
Most production systems we ship use both. The question isn't "which one." It's "where does each one earn its place."
Most consultancies sell strategy slides. Three questions separate builders from deck-makers.
You don't pay in license fees. You pay in workflow drift — and that bill compounds.
A POC that can't ship is an expensive demo. Three rules to make yours actually inform the decision.
Frontline workers, clinicians, analysts — the people who actually use enterprise AI often start out skeptical.
Frontline AI at retail scale isn't a feature. It's a platform decision. Three lessons.
No posts in this category yet. Show all posts →
More posts publishing weekly. Subscribe to be notified — or check back.