Engineers showcase Jev-based system-one applications
At the AI Engineer Code Summit, engineers from Glean, UiPath and Workday presented applications and prototypes built with Jev and other system-one models. These non-generative models return structured choices, scores or probabilities and are typically faster and cheaper than reasoning LLMs, according to Latent Space. Examples included Glean using Jev alongside LLMs and classifiers, UiPath testing document ranking through a multi-round “tournament,” and Workday prototyping an interface that fills a time-off card while the user types. TypeSafe AI CEO Diogo Almeida argued that system-one models should be integrated directly into code and called Jev “reliable intelligence,” a vendor claim the report did not independently verify.
The presentations illustrate a distinct AI-integration approach: engineers are using structured, non-generative models alongside LLMs for specific application decisions such as ranking documents and completing interface actions.

Today at the AI Engineer Code Summit, the main theme was system one models — non-generative models that return structured choices, scores, or probabilities. They’re also typically much faster and cheaper than reasoning LLMs (a.k.a. system two models).
And who better to give an inspirational rallying cry for system one models than Diogo Almeida, co-founder and CEO of TypeSafe AI. Almeida was lead creator of Jev, the product that kicked off this trend less than two months ago.
Jev was an instant revelation for AI engineers when it was released in September. In a podcast with Latent Space on launch (which quickly became our most popular episode of the year), Almeida explained the core problem with making LLMs the heart of software: reliability.
In his keynote at AIE Code today, he took it a step further by claiming that Jev is “reliable intelligence” that should be used for “just automating everything.”
#Jev#TypeSafe AI#Glean#UiPath#Workday#AI Engineer Code Summit