← All use cases

Task-completion check

Before an agent stops, ask Jev whether the work is actually finished and the claims hold up.

Coding-agent use case · output & completion checksawesome-jev-by-typesafe

Agents love to declare victory early. "Diff verification" and "agent output checks" in the awesome-jev catalog cover the stop decision: before an agent ends its turn, verify that the task is genuinely done and that its claims are backed by evidence (tests actually passed, the change addresses the ask). Jev's statement-verification shape — a calibrated yes/no against the task, the diff and the test output — is exactly the primitive TypeSafe's own docs recommend for "checking whether a statement is true of a record before taking an action." Below a threshold, the agent keeps working instead of handing back a half-finished job.

Try it live

This is the real thing, not a mockup. Edit the input, hit Run, and Jev returns every typed answer in one round trip — free, no signup. Now picture the same call fired across thousands of items in parallel.

POST jevtypesafeai.com/api/v1/decide
state — the input software gives Jev384c
questions — the typed decisions you want back
noulcomplete
Does the change actually address the stated task?
→ probability 0.0 … 1.0
noultests_back_it
Does the test output provide real evidence the fix works (not just unrelated passes)?
→ probability 0.0 … 1.0
scoreconfidence
How confident should the agent be that it's safe to stop and hand back?
→ 0…3 · 4 levels
real API · free · no signup
Typed, calibrated output appears here.
Pick a demo, tweak the input, and hit Run Jev.
Get an API key →← All use cases

The decisions Jev makes

In a single call, Jev evaluates each of these — in parallel, against the same input:

noulcomplete

Does the change actually address the stated task?

returns a calibrated yes/no probability.

noultests_back_it

Does the test output provide real evidence the fix works (not just unrelated passes)?

returns a calibrated yes/no probability.

scoreconfidence

How confident should the agent be that it's safe to stop and hand back?

rates it on an ordered scale:

  1. keep working
  2. borderline
  3. likely done
  4. clearly done

The exact request

This is the real payload behind the live demo — copy it, change the state, and you're building:

{
  "model": "jev-latest",
  "state": "Task: \"Fix the bug where refunds over the order total are silently accepted.\"\n\nAgent's final summary: \"Added a balance check in process_refund so over-total refunds now raise RefundError.\"\n\nDiff: added `if amount > order.remaining_balance: raise RefundError(...)` before the gateway call.\n\nTest output: `test_refund_over_total PASSED · test_refund_partial PASSED · 2 passed, 0 failed`",
  "questions": {
    "complete": {
      "type": "noul",
      "instructions": "Does the change actually address the stated task?"
    },
    "tests_back_it": {
      "type": "noul",
      "instructions": "Does the test output provide real evidence the fix works (not just unrelated passes)?"
    },
    "confidence": {
      "type": "score",
      "instructions": "How confident should the agent be that it's safe to stop and hand back?",
      "criteria": [
        "keep working",
        "borderline",
        "likely done",
        "clearly done"
      ]
    }
  }
}

Wire it into your code

Read the typed answers and branch in plain code — no parsing. Auto-handle the high-confidence cases and route the uncertain ones to a bigger model or a human. It's one API call and output is free, so ask every question you need at once.

Build your own

Every scenario above is a single API call. Try any of them free in the playground, then get a hosted key to ship it in minutes.

Run this demo ▶Get an API key →
Task-completion check — a Jev use case with a live demo · Jev by TypeSafe AI