MCP servers put Jev inside agent environments. Typesafe MCP is a single-binary Go server exposing one evaluate tool for Noul, Choice, and Score questions with one-command registration for Claude Code, Claude Desktop, and Codex; jkudish-jev-mcp and others take similar approaches.
They are the most common way Jev reaches a coding loop without the agent writing SDK glue, and they pair naturally with the agent skill that teaches good question structure.
A single-binary Go MCP server exposing one evaluate tool for noul, choice, and score questions, with one-command registration for Claude Code, Claude Desktop, and Codex.
An MCP server exposing ten Jev judgment tools, including verify, screen, find, rerank, classify, review, and gate, each returning typed probabilities in roughly 150 to 500 ms.
Say the moment and get reaction GIFs: Jev picks a reaction and literal subjects, then scores a KLIPY shortlist of up to 30 candidates from titles and tags.
jev is the best excuse you could possibly have to go re-read 12 factor agents. Tool calling itself can be decomposed into classify+action,
if you learn to design ai programs as pipelines that switch breathlessly between classification, structuring data, deterministic code, ANDShow more
Dillon Mulroy
@dillon_mulroy
i think jev is resonating with devs so well b/c it unlocks so many opportunities for composing ai into systems and products rather than ai _becoming_ the product/system
really does feel like it was a missing primitive
Jev is one of the more interesting model launches I have seen recently because it asks a very simple question:
Why are we using autoregressive LLMs as insanely expensive if statements inside software?
The easiest way to think about it is:
LLM:
text -> generate tokensShow more
Diogo Almeida
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x
Jev just landed and the agent stack moved in three days.
TypeSafe AI released Jev on September 15. It is built for the work agents actually do most of the time: choose the next tool, score a risk, decide whether to retry, or answer yes or no. Latency is under half a second.Show more
got @typesafeai’s new model Jev to play Super Mario Bros.
fast inference + structured outputs makes it surprisingly good for real time use cases.
I'm excited to see what can be done with these new models!
this is the easiest way to understand Jev:
LLMs generate answers.
Jev makes decisions.
that sounds like a small difference, but it actually changes the entire use case.
say you give a normal LLM this:
“here’s a user, their account history, payment behavior, support chats,Show more
Diogo Almeida
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x
