---
title: The first job I'm giving Jev is checking whether my agents are done
date: 2026-09-23
summary: a model that only answers typed questions fits agent supervision; I start with "is it really done?", in shadow mode
---
I run several coding agents in parallel. What slows me down is not their
work but checking it: is this one finished, stuck, waiting on me, or saying
"done" when it is not? These are small questions with a handful of possible
answers, and I ask them dozens of times a day.

TypeSafe released a model built for that kind of question on 15 September
2026.[^1] Jev does not write text: it takes some state and a list of typed
questions, and returns an answer to each with a probability.[^1] There are
three question types: pick one of N options, rate on an ordered scale, or
yes/no.[^2] TypeSafe announces responses in 70 to 500 ms and $0.042 per
million input tokens, with output free.[^1]

## What the numbers do not tell me

Every figure so far comes from TypeSafe, and nobody outside has tested it
yet.[^3] In TypeSafe's benchmark the reference answer is the average of two
frontier LLMs, and TypeSafe's own team wrote the workflows.[^2] On one
comparison Jev matched the LLM it replaced, 67.8% against 67.9%, rather
than beating it.[^4] The claim is equal quality at a fraction of the time
and cost, measured against other models.

So my question is narrower: does it agree with me, on my agents, often
enough to act on?

## Where it fits in supervising agents

The founder argues for splitting AI work into small decisions that can be
checked one by one, instead of one large prompt.[^5] Supervising agents
already has that shape:

- **Stuck or looping.** Read the last screen of each agent's terminal every
  minute and pick one: working, looping, waiting for input, crashed.
- **Done, really.** When an agent stops, compare the task, its final
  message and the diff: done, says done but is not, asking me, blocked.
- **How much review.** Rate a finished change from "merge on green checks"
  to "read it carefully".
- **Routing.** Pick which agent or model tier gets a new task.
- **Ready to hand off.** Yes or no: is this task specified well enough for
  an agent to start without guessing?

All five come up often, have bounded answers and small inputs, and a wrong
answer costs me a second look, not a broken release.

## The first one I test

I start with "done, really". In my setup it needs nothing new to trigger:
both agents I use already run a hook when they stop. And the correct answer
shows up on its own: either I accept the work, or I send the agent back.
A community plugin already checks "done" claims with Jev,[^6] so the idea
is not exotic; I want the numbers on my own work.

It runs in shadow mode. At each stop, a hook saves the task, the agent's
last message and the diff, then Jev's answer, then what I did next. After
two weeks I compare Jev's answers with my own decisions, repo by repo, and
set the threshold from that data rather than from a benchmark. Each call carries its whole state,[^2] so I can save
cases before I have access and replay them once I do.

If agreement is high, the next step is letting it send an agent back on its
own when it answers "says done but is not". If it is low, the logged cases
will show where it goes wrong.

[^1]: Diogo Almeida, "Introducing System One Models & Jev", TypeSafe AI Blog, 2026-09-15. https://typesafe.ai/blog/introducing-system-one-models-and-jev
[^2]: MarkTechPost, "TypeSafe AI Releases Jev: A System One Model That Returns Typed, Calibrated Decisions Instead of Text", MarkTechPost, 2026-09-19. https://www.marktechpost.com/2026/09/19/typesafe-ai-releases-jev/
[^3]: MindStudio, "RLCD vs RLHF: What Is Typesafe's Jev Model Actually Claiming?", MindStudio Blog, 2026-09. https://www.mindstudio.ai/blog/typesafe-jev-rlcd-vs-rlhf
[^4]: Anthony Maio, "Jev: The Language Model That Won't Talk", Substack, 2026-09. https://anthonymaio.substack.com/p/jev-the-language-model-that-wont
[^5]: Latent Space, "Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI", Latent Space, 2026-09. https://www.latent.space/p/jev
[^6]: APIMaster.AI, "How to Use Jev in Claude Code and Codex: Four Routes That Work", APIMaster.AI Blog, 2026-09. https://apimaster.ai/blog/jev-claude-code-codex
