AI evaluation and model routing: test before you trust

How to test an AI system before it carries real work: golden sets, eval harnesses, a second reader, and the cheapest model that clears your bar. Results come with the cost per thousand decisions.

AI ENGINEERING01

Jev 1.13 Tested: Its Router’s Accuracy for 2 Cents per 1,000 Decisions

TypeSafe’s Jev 1.13 only decides; it never writes. Picking AI model sizes for 94 of our tasks, it scored 73 to its own router’s 72, in a fifth of a second and for about 2 cents per 1,000 decisions.

SEP 25, 2026 · 9 MIN READ
AI ENGINEERING02

A Second Reader Catches What the First One Missed. Not What Retrieval Missed.

Two models answering independently from the same retrieved passages catch each other’s misreadings, because their mistakes are not the same mistakes. What neither of them can catch is a passage that should never have been retrieved — and that is the outcome the mechanism reports as healthy.

SEP 22, 2026 · 8 MIN READ
AI ENGINEERING03

The Cheapest Model That Clears Your Eval Bar Is the Correct Model

Most teams pick a frontier model in the kickoff meeting and never revisit it. That is not a technology decision — it is the absence of one. Here is what a routing harness actually looks like, and the three places a cascade quietly breaks.

AUG 19, 2026 · 9 MIN READ
AI ENGINEERING04

AI Integration Projects Need a Check on the Output, Not a Better Model

AI integration projects mostly stall on workflow, not on the model, according to MIT’s 2025 study. Before scaling one, build a check that catches a wrong answer before it reaches a customer, a regulator or print.

AUG 19, 2026 · 5 MIN READ