AI IDE List

Jev: an AI decision model for agents

TypeSafe’s Jev selects from predefined options, scores text against a rubric, and returns yes/no probabilities. Use it to route tools, select agent skills, and check results.

Sources checked September 19, 2026 · View sources

Example inputs and outputs

Input

Find why our checkout API started returning 502 after the last deployment.

Available specialists: backend, infrastructure, frontend, database.
Jev evaluates three questions
Choice

Which specialist should handle this?

backend72% option probability
Noul

Does this need investigation?

0.98probability of yes
Score

How urgent is the issue?

3.6 / 4Urgency · 0–4 rubric

Application actionRoute to the backend agent. Let it investigate and write the fix.

Illustrative outputs · No live API call · No actions are executed

Output typesChoice, Score, NoulOptions, rubric scores, and yes/no probabilities
Input price$0.042 / million tokensOutput is not charged. Pricing source
Current modelJev 1.13Hosted API · Text input

Jev videos & use cases

End-to-end testing with Jev and agents

Oskar demonstrates Jev in e2e, a framework for running end-to-end tests with agents across web and mobile.

The announcement describes an open-source framework in development, with availability coming soon.

How Jev turns text into decisions

Send relevant text and a specific question. Jev returns a value that your application can use in a conditional, ranking, or review rule.

Deterministic rule
if (amount > 1000) {
requireApproval()
}

Ordinary code handles exact rules.

Semantic judgment
“Did this tool result
actually solve the task?”
→ probability of yes: 0.94

Jev handles a narrow judgment. Your code chooses the next step.

When a decision depends on text meaning

Handwritten rules struggle with fuzzy language. A full LLM can make the call, but you may only need a category or a yes/no estimate.

Define the possible decisions, give Jev relevant state, and keep policy in your application.

TypeSafe · What Jev does

Jev’s role in an agent workflow

A user task goes to Jev for routing, then to code or tools, an LLM for reasoning and generation, or human review. Results go through a Jev check, then application code accepts, retries, or escalates. Retry returns to routing.
A suggested architecture. Jev supplies a judgment; your application owns permissions, execution, and verification.

Choice, Noul, and Score outputs

You define the question and its meaning. Jev returns values you can branch on, rank, or check against a threshold.

Illustrative outputs below, not measured API responses.

ChoiceSelect one option

“Who should investigate this checkout API failure?”

Backend72%
Infrastructure21%
Frontend5%
Database2%
Tool selection · Skill routing · Classification

NoulEstimate the probability of yes

“Did the previous tool call solve the task?”

0.94
0 · No1 · Yes
Completion checks · Retry gates · Review gates

ScoreScore against a defined rubric

“How risky is this code change?”

3%
0
11%
1
59%
2
23%
3
4%
4
  • 0 Safe
  • 1 Low
  • 2 Medium
  • 3 High
  • 4 Critical
2.14 / 4Probability-weighted score
Risk triage · Relevance · Rubric-based evaluation

How to interpret these values. Choice and Score include a separate confidence statistic derived from their distributions. Noul returns the probability of yes. None guarantees a correct judgment.

Evaluate multiple questions in one request

Ask about relevance, risk, and completion in a single request. Each question reads the same state, not the other answers. Combine the results in code.

TypeSafe · Parallel questions
state
  • Is this relevant?Noul
  • How risky is it?Score
  • What next?Choice

Jev use cases and published results

Examples of browser action selection, skill routing, context filtering, and output evaluation, with sources and test limitations.

Browser Use project recording · Google Flights · 1× speed · Silent video

Browser Use: select browser actions

Project-author measurements

Jev chooses the browser operation and target element from DOM state. Mercury generates text only when TYPE_TEXT is selected.

7.073sone recorded Google Flights run
Test scope and limitations

Project-author measurement. Three matched pairs on one task and browser profile; not a general reliability benchmark. Initial navigation and independent verification are outside the timer.

Browser Use · Measurements & limits

Hermes: select from 182 agent skills

Vendor cookbook

One pass ranks the catalog and asks whether a skill is needed. A second reads the top three in detail, then suggests one skill—or none.

16.8% → 7.3%wrong-skill load rate
Test scope and limitations

Vendor cookbook: Jev 1.12 with Claude Haiku 4.5, 488 requests. Wrong loads are measured on 315 covered requests; unnecessary loads on 173 uncovered requests fell from 9.8% to 4.0%. Partly synthetic data.

TypeSafe · Hermes skill suggestion

Claude Code: filter tool history

Community project

This Claude Code plugin asks which tool calls and results still matter. It keeps, truncates, or drops them instead of rewriting everything as a summary.

Verbatimcontent that survives compaction
Test scope and limitations

Community implementation, not a measured accuracy guarantee. Selection can discard useful evidence; evaluate it on your own sessions.

fast-jev-compaction · Source code

Every: check text against writing criteria

Third-party experiment

Every’s head of evals checked 37 texts against 21 writing patterns: 777 judgments in under 0.7 seconds, at an estimated cost of $0.0025.

777judgments across 37 texts
Test scope and limitations

Small third-party experiment, not a production accuracy study. In a separate 12-passage test, Jev caught 6 of 7 planted defects; Fable 5.1 caught all 7.

Every · Mike Taylor’s hands-on evaluation

Document re-ranking. A TypeSafe legal retrieval cookbook uses Jev to re-rank a BM25 shortlist by relevance to a query.

See the cookbook

Jev in a coding agent workflow

A coding agent can call Jev before selecting a tool, when filtering context, or after receiving a result. These integrations require setup.

Model, skill, and tool selection

  • Route to the right model or specialist
  • Shortlist relevant agent skills
  • Select an available MCP tool

Context filtering and action checks

  • Filter old context and tool results
  • Check whether evidence is relevant
  • Flag actions for a policy check

Result verification and retry decisions

  • Check results against narrow criteria
  • Decide whether to retry or escalate
  • Send uncertain decisions to review

Integration patterns, not built-in features of every coding agent. Tool permissions, tests, and approval rules stay in your application.

Jev vs. GPT and Claude structured outputs

Both can return structured decisions. Compare their output types, confidence signals, supported tasks, and costs.

What changesGPT / Claude structured outputJev
Core jobGenerate text, code, or a structured answerMake a bounded semantic decision
OutputGenerated tokens constrained to a schemaA choice, rubric score, or yes/no probability
Schema guaranteesStrict output modes can enforce a supported schemaThe interface returns predefined typed decisions
ConfidenceA requested confidence number is usually self-reportedChoice / Score confidence is derived from the distribution
Several checksBatching and parallel requests depend on the APIIndependent questions share state in one request
Reasoning & writingUse for explanations, code, and multi-step reasoningUse for routing, filtering, scoring, and checks
CostDepends on model, input, output, and caching$0.042 / 1M input tokens; output is not charged

Schema guarantees are not unique to Jev. Evaluate the accuracy and total cost of the complete workflow.

OpenAI · Structured output guarantees

Published Jev benchmarks

TypeSafe reports speed and cost for its System One workflows. PrimeLine separately tested classification accuracy on 800 commit messages and 450 knowledge-base notes.

TypeSafe’s speed and cost comparison

View vendor methodology
TypeSafe website screenshot showing LM, LLM, RLHF, RLVR, and RLCD model categories, with Jev speed and cost figures alongside Claude and GPT models.
TypeSafe website screenshot · Vendor-reported comparison · September 19, 2026View full size
Third-party benchmark

PrimeLine: four models, two classification jobs

Read the full test
Commit messages800 items · Accuracy
Jev
65.8%, highest observed accuracy
Claude Opus 5
63.5%
GPT-5.6
59.5%
Claude Haiku 4.5
54.6%
Knowledge-base notes450 items · Accuracy
Jev
90.7%
Claude Opus 5
86.9%
GPT-5.6
92.7%
Claude Haiku 4.5
97.8%, highest observed accuracy

Reported September 18, 2026. Unanswered items count as incorrect. Jev’s numerical lead over Opus on commits was not statistically distinguishable in this sample. Dataset provenance and task-specific labels limit generalization; these are not universal model rankings.

A schema-valid answer can still be the wrong judgment.

“Zero hallucinations” refers to the constrained output shape. A valid approve can still be an incorrect decision. Evaluate accuracy, calibrate thresholds, and keep a fallback.

TypeSafe · Introducing Jev

Jev 1.13 limitations

TypeSafe reports weaknesses in exact calculation, multi-hop reasoning, and noisy context. The alternatives below address each case.

Math, counting & exact dates

Use deterministic code

Extract values, then calculate or compare them in code.

Deep, multi-hop reasoning

Use a reasoning model

Break a broad question into small checks, or hand it to an LLM.

Writing, coding & explanations

Use a generative model

Jev can judge a proposed output. It does not create it.

Huge, noisy or adversarial context

Retrieve, clarify & validate

Filter irrelevant text, resolve conflicting criteria, and treat inputs as untrusted.

Read the official model limitations

Jev 1.13 pricing and API limits

Published Jev 1.13 pricing, checked September 19, 2026. Confirm current terms with TypeSafe.

Per million input tokens$0.042

Output is not charged.

Official pricing and limits
Model ID
jev-1.13.0
Input
Text, including JSON text state
Context
64K tokens per request
State + longest question: up to 32K
Published rate limits
250K tokens/s · 1,200 requests/min
TypeSafe says these limits can change.
Access
HTTP API · TypeScript / JavaScript · Python

Call Jev with TypeScript or Python

Pick a judgment you already make repeatedly. Define the options. Evaluate against known answers before automating it.

  1. 1
    Get an API key

    Create a key in the TypeSafe console. Keep it server-side.

  2. 2
    Define the question and options

    Supply relevant state and clear categories. Include a review path when information is missing.

  3. 3
    Evaluate on labeled examples

    Check accuracy, confidence thresholds, latency, and total cost on your actual workload.

$npm install @typesafe-ai/sdk
route-task.ts
import { choice, TypeSafeClient } from "@typesafe-ai/sdk";

// Server-side only. Set TYPESAFE_API_KEY in the environment.
const client = new TypeSafeClient();
const response = await client.systemOne({
  model: "jev-1.13.0",
  state: { task: "Investigate checkout API 502 errors." },
  questions: {
    specialist: choice("Which specialist should investigate?", {
      backend: "Application code and API behavior",
      infrastructure: "Networking, deployment, or runtime failures",
      review: "Insufficient information to choose a specialist",
    }),
  },
});

const decision = response.answers.specialist;
// Illustrative threshold: evaluate it on your own labeled tasks.
const next = decision.confidence >= 0.9 ? decision.choice : "review";
console.log({ next, probabilities: decision.probabilities });

Run on your server with TYPESAFE_API_KEY set. Your actual response will vary.

Frequently asked questions

What is Jev, in plain English?

Jev is TypeSafe’s AI decision model. Give it relevant text and a specific question; it returns a choice, a score, or a yes/no probability that your code can use. It does not write the reply, generate code, or explain its reasoning.

TypeSafe · What Jev does
Why not just ask GPT or Claude for JSON?

You can, and a strict structured-output mode can also guarantee a supported schema. Jev’s difference is a decision-focused interface, distributions rather than a generated confidence claim, and a low published input price. Whether it is better depends on your task’s accuracy, latency, and cost requirements.

TypeSafe · Choice, Score & Noul
Isn’t this just classification?

Classification is one of its jobs. The useful part is that you define different categories, rubrics, and yes/no questions at runtime. TypeSafe says it does not fine-tune or LoRA-adapt Jev for each customer; domain knowledge and rules go into the request.

TypeSafe · Models, pricing & limits
What does a probability or confidence of 0.9 mean?

For Noul, 0.9 is the model’s estimated probability that the answer is yes. For Choice, each option has its own probability. Choice and Score also return a separate confidence statistic derived from the distribution; it is not simply the winning option’s probability or a guarantee of 90% accuracy on your task. Validate thresholds with representative labeled examples.

TypeSafe · Probability vs. confidence
What does a score such as 2.14 mean?

It is the probability-weighted mean of the rubric’s level numbers. On our illustrative 0–4 risk scale, 3%, 11%, 59%, 23%, and 4% produce 2.14. That is a position on your chosen scale, not a 2.14% risk or a universal quality score. Inspect the full distribution as well.

TypeSafe · Reading a Score
Does “zero hallucinations” mean Jev is always right?

No. A constrained output shape prevents an answer outside the interface, but a valid choice can still be the wrong decision. Test its judgments, keep deterministic checks, and define fallback or review paths. Schema validity and decision accuracy are different properties.

TypeSafe · Introducing Jev
Can I use Jev with Claude Code or Codex?

Yes, through an integration you build or a compatible community project. Jev can select skills, filter context, choose tools, and check results around a coding agent. The fast-jev-compaction project specifically targets Claude Code. These examples are integration patterns, not a claim that either coding agent includes Jev by default.

fast-jev-compaction · Source code
Can Jev see screenshots or run locally?

Jev 1.13 accepts text, including structured text state. It does not accept image, audio, or video input. It is offered as a hosted API; the open-source example projects are integrations, not downloadable Jev model weights.

TypeSafe · Models, pricing & limits
Can one question depend on another in the same request?

Questions in a request are evaluated independently against shared state. They do not read each other’s answers. Combine the outputs in your application; if a later question needs an earlier answer, make a subsequent request.

TypeSafe · Choice, Score & Noul

Sources & editorial notes

This is an independent AI IDE List explainer. Official specifications, vendor tests, community projects, and third-party experiments are labeled separately. Numbers are dated snapshots, not guarantees. Interactive outputs and custom diagrams are explanatory illustrations.

View all 18 references

TypeSafe API documentation

Read the Jev quickstart