ship an agent that does the work. let jev evals and policies judge every move it makes.
bring an agent that does real work: support, payments, ops, coding or sales. write jev evals and policies for it, then demo the run where a verdict caught a bad action and steered it right. solo or in a team, three and a half hours, judged live.
jev from typesafe ai returns typed verdicts (choices, scores, yes/no) instead of text. that makes it a sharp, cheap judge for an agent while it runs, not after. score every action, check it against a policy, and decide on the spot whether the agent proceeds, stops, or gets told what to do instead.
anyone can build a safe agent that summarizes docs. we want the agent you'd be nervous to ship, made trustworthy by jev.
support, payments, ops, coding, sales. anything where a wrong action costs something.
the evals score every action it takes. the policies decide what happens next.
show a run where a jev verdict caught a bad action and steered the agent to the right one.
a lab for the deeply curious.
lossfunk is a lab in bengaluru for people working on big, underdefined problems, from minds and intelligence to science and discovery. it runs a fully funded sabbatical, a paid fellowship and a six-week residency for researchers and builders.
to winthe highest-impact, highest-risk use case that runs reliably.
how much damage could this agent do if it went wrong?
does it hold up across runs, not just the one you rehearsed?
a clear moment where a jev verdict changed what the agent did.
ambitious and shaky loses to ambitious and solid.
jev evals and policies walkthrough
ship the agent, then write its jev evals and policies. failproof runs them on live tool calls.
show a run where a jev verdict caught a bad action and steered the agent right.
the highest-impact, highest-risk use case that runs reliably takes it.
your laptop, your charger, and an agent idea, or a half-built one you want to finish. come solo or as a team.
the build block runs just under two hours, so arrive with the idea picked and your setup ready.
yes, ideally. get jev access through openrouter or the early access waitlist at typesafe.ai, and sort it out before sunday: build time is tight.
no access yet? come anyway, we'll pair you up with someone who has it.
yes. failproof will be set up at the venue, so your jev policies run on live agent tool calls.
when a verdict says stop or instruct, you see the agent change course as it runs, not in a report afterwards.
yes. came to jev colearn? this is the sequel.
didn't? the 3:00 pm kickoff walks through jev evals and policies from the start, so you'll catch up in the first 15 minutes.
register on luma. every registration is subject to host approval, so apply early.
once you're approved, luma sends the confirmation and the day's details.
failproof is your agent's oversight layer, steering it towards success. it traces your agents, finds failure patterns over time and sets up rules to prevent them from happening again.
jev evals and policies just launched on failproof, for better reliability at the least cost and latency. the open-source cli is free: npm i -g failproofai.