let the building begin!! a simple guide on what makes jev special, how to use it w/ your agents, and a few model use cases: x.com/sydneyrunkle/s… x.com/typesafeai/sta…
View on XWhat the people building AI are posting.
Straight from X: the labs, the researchers and the builders worth following, in one place and in the order they posted.


another super compelling use case that i didn't touch on the blog -- "jev as a judge" for evals jev is cheaper, faster, and more reliable (consistent) than the LLM as a judge alternative read the full blog: x.com/LangChain/stat… x.com/sydneyrunkle/s…
View on X
jev as a Judge proves to be a cheaper and more precise alternative to LLM as a judge for online evals. great guide from Sean and Daniel on why Jev is great for evals, an experiment vs other LLMs, and how to try this out for your agents! x.com/LangChain/stat…
View on X
jev is so exciting! so you started using jev, now you need to know 1. what decisions is jev making? (observability) 2. is it making the right ones for my application? (evals) 3. how can i help jev make better decisions? (engine) and for obs+evals+engine, you need langsmith langchain.com
View on X
a few months ago we wrote about "graph engineering" for agents with langgraph jev fits really nicely into graphs for classification steps x.com/sydneyrunkle/s…
View on X
super cool use case -- browser use w/ jev! would highly recommend following work from @ndrezn for great agent dev content x.com/ndrezn/status/…
View on X
super pumped for this convo w/ @huntlovell and @allietheicon on all things langchain 🤝 jev x.com/LangChain/stat…
View on X
great callout from @ktech9999 on a use case jev is going to transform x.com/ktech9999/stat…
View on X
instead of generating text, jev from @typesafeai generates structured output this makes it great for classification tasks like model routing, tool selection/search, and guardrails of many forms! it's also ridiculously fast and cheap compared to LLMs doing the same tasks
View on X
right now, a lot of agents perform classification tasks / steps if you can replace those steps with a model that's optimized for classification, you can massively reduce latency and cost i think jev is re-kindling the "graph engineering" phase of agent design x.com/sydneyrunkle/s…
View on X
i normally would not post this late, but wanted to share what @huntlovell and I have been jamming on. @typesafeai just released Jev, a new type of classification model. it's really popular right now because it's ridiculously fast and cheap (up to 200x / 400x reductions vs comparable LLMs on classification tasks). learn all about Jev and how to build it into your harness!
View on X

had to turn auto mode off in my coding agent before bc the classification was slow turning it back on now that we're using jev!
View on X
Posts appear as published on X and link to the original. Replies and reposts are left out, and anything older than 14 days drops off.


