A browser agent that finds flights in seven seconds. A Claude session cut from a million tokens to 86,000 in one second. A WHERE clause that reads plain English. Vercel's safety reviewer. We are collecting what people built with Jev in its first days, and what they argued about, each in their own words. Nobody in these bylines is on eChai, and every entry links back to where it was posted.
7 entries Clear
Higgsfield, whose API fronts fifty generative models, has Jev pick the most cost-effective model for each request.
Higgsfield
3h
We found the perfect use case for Jev: auto-routing GenAI models.
The idea: Jev picks the most cost-effective models for your task, balancing speed and quality.
All generations made with Higgsfield API.
Ian Nuttall on the quickest way in: TypeSafe publishes a skill, one command installs it, and a prompt in your own project asks where Jev could replace a slow model call.
Ian Nuttall
6h
Unsure how to get started with Jev?
Install the skill:
npx skills add typesafe-ai/skills --skill typesafe-ai
Then prompt in your project:
use /typesafe-ai to see how Jev can be used to replace slow, expensive LLM usage and find possible new features it would enable for users.
Vercel's own note on the same day, with the call as it reads in the AI SDK: a model, a state and a set of questions.
Vercel Developers
1d
Jev from @typesafeai is on AI Gateway.
Build agents that decide, route, score, and stop in milliseconds:
𝚊𝚠𝚊𝚒𝚝 𝚎𝚟𝚊𝚕𝚞𝚊𝚝𝚎({
𝚖𝚘𝚍𝚎𝚕: '𝚝𝚢𝚙𝚎𝚜𝚊𝚏𝚎-𝚊𝚒/𝚓𝚎𝚟',
𝚜𝚝𝚊𝚝𝚎,
𝚚𝚞𝚎𝚜𝚝𝚒𝚘𝚗𝚜,
});
Dan van der Merwe wrote an Effect service for Jev so it drops into effect-agent.
Dan van der Merwe
1d
I've been playing around with Jev in effect-agent and so I built a simple effect service for it. This model is super awesome by the way!
Two days after launch Jev was a model on Vercel's AI Gateway, which is what let several of the browser and agent demos on this page call it without a TypeSafe key.
TypeSafe AI
1d
Jev is now available on the @vercel AI Gateway
LangChain's engineering post, two days after launch, wiring Jev into an agent harness as middleware in two places: choosing the model per request, and checking a tool call for risk before it runs, the same job Vercel's fx safety reviewer does. Both are LangChain middleware.
Sydney Runkle and Hunter Lovell, LangChain, in langchain.com
A simple lookup doesn't need the same model as a difficult debugging task. Model-routing middleware lets Jev assess the request and choose a model based on criteria you define, so fast and inexpensive for straightforward tasks, more capable for complex ones.
[...]
AutoModeMiddleware uses Jev to check tool calls for risky decisions it may take, and block calls before the tool executes.
The funding, from the press release: a $40 million seed led by DCVC, where James Hardiman is a general partner. TypeSafe was founded in 2024 in San Francisco by Diogo Almeida, Erik Gafni and Sasha Sheng. Forbes reported the round at a $200 million valuation.
James Hardiman, DCVC, in Yahoo Finance
TypeSafe is approaching one of the biggest remaining challenges in AI: turning increasingly capable models into technology that developers can reliably build into products at scale.
