Field notes from shipping AI.
What we're building, what we're tuning, what we're getting wrong. Subscribe via RSS.
- 01tutorial·May 24, 2026
How to read AI model benchmarks in 2026 (and what to ignore)
The benchmark scores you see in launch posts and vendor comparisons are mostly noise for production decisions. Here's what the numbers actually mean, which benchmarks track real-world performance, and what to test on your own data instead.
- 02opinion·May 23, 2026
The hidden cost of model-agnostic AI architecture
Model-agnostic architectures sound prudent and future-proof, and we recommend them most of the time. But there's a hidden cost most teams don't price in until they're a year deep. Here's what to know.
- 03opinion·May 22, 2026
When NOT to build an AI chatbot (and what to build instead)
Chatbots are the default AI build for businesses, and the default is often wrong. Here's when a chatbot is the right call, when it isn't, and what the better alternative looks like.
- 04tutorial·May 21, 2026
Five patterns we see in successful AI implementations
The teams that ship AI to production and keep it there share a small number of predictable patterns. None of them are about the model. Field notes from the engagements we've run.
- 05field-notes·May 20, 2026
Why most AI POCs die between month two and month four
About 1 in 4 AI proofs-of-concept never make production. The failure mode is almost always operational, not technical — and it's predictable enough to design around. Here's what kills them.
Send us your most expensive operation.
We'll have an audit on your desk in five days.
One PDF. No deck. No obligation. We'll tell you whether AI is the right answer for it — and if it is, we'll quote the build the same week.