Awesome Jev Use Cases

September 18, 2026 · View on GitHub

Real use cases, working patterns, and hard-won guidance for building with Jev, TypeSafe AI's System One model — the model that returns typed, probabilistic decisions instead of text.

Jev is not a chatbot. You send it program state and typed questions; it returns typed answers with calibrated probabilities in 70–500 ms. This repository collects what people have actually built with it, and - more importantly - how to use it efficiently and effectively.

state + typed questions -> typed answers + probabilities -> your code decides

Status: research snapshot as of 2026-09-18. Jev is in early access and moving fast. Prices, limits, and aliases will change. Every claim below links to its source.


Start here

If you want to…Go to
Understand what Jev is and when to reach for itdocs/what-is-jev.md
Make your first call in five minutesdocs/getting-started.md
Learn the design methoddocs/how-to-use-jev-effectively.md
Steal a proven architecturedocs/patterns.md
Avoid the mistakes everyone makesdocs/failure-modes.md
Decide Jev vs LLM vs a classifierdocs/model-selection.md
Verify it works on your datadocs/evaluating-jev.md
See the full use-case catalogusecases/README.md
Browse real applications people builtreference/showcase.md
Copy a runnable exampleexamples/
Find ready-made questionsreference/question-catalog.md

The 60-second version

Jev is TypeSafe AI's first System One model, launched 15 September 2026 by Diogo Almeida (former OpenAI researcher, co-author of the InstructGPT paper) with roughly $40M in seed funding led by DCVC. The name comes from Daniel Kahneman's Thinking, Fast and Slow: LLMs are deliberate System 2 thinkers, and most decisions inside software only need a fast System 1 reflex.

You get exactly three question types, and that is the design, not a limitation:

PrimitiveYou declareJev returns
ChoiceA list of options (up to 255)The chosen option, a probability per option, a confidence
ScoreAn ordered rubric (2–10 levels)A score (can land between levels), a distribution, a confidence
NoulA statement about the state (yes/no)A single probability 0–1

All questions in a request are evaluated in parallel and in isolation against the same state. Adding a tenth question costs tokens but barely any time. That single property is what unlocks most of the patterns in this repo.

The economics, vendor-reported: $0.042 per million input tokens, output free, 70–500 ms end to end. On TypeSafe's own four-workflow evaluation Jev scores 67.8% agreement with a frontier-model consensus at $0.0004 per case, versus GPT-5.6 Terra at 67.9% and $0.0304. Read model-selection.md for the honest breakdown, including why those multipliers are softer than the headline.


What people have built

Jev launched on 15 September 2026. Within three days the community had shipped browser agents, trading bots, drones, code reviewers, and a semantic firewall. This is a sample - each entry links to the repository, and reference/showcase.md has the full detail plus 100+ more.

ProjectWhat it doesHeadline result
browser-use/jev-ultrafastBrowser agent with a dynamic action space. Jev picks the operation and the target; a small LLM writes text only when the step needs itZürich → London on Google Flights in 7.1 s for $0.0039
TheoLeeCJ/openjevReproduces the Jev interface on a frozen 4B model by reading option logits instead of generatingNo waitlist; runs in a browser
tamaratran/fast-jev-compactionReplaces Claude Code's lossy compaction summary with Jev keep/delete decisionsKept content stays verbatim - nothing is rewritten
jarrodwatts/jev-traderMarket maker on Kuru MON-USDC. One buy/sell decision per Monad block81 ms model latency, 2 RPC round trips per block
fhshaik/typesafe-marioPlays Super Mario Bros. from emulator RAM as object-centric JSONNo screenshots sent to the model
thruwire/foremanIndependent supervisor above Codex workers: is the work complete, tested, off-track, stuckFramed honestly as an architecture experiment
devagrawal09/jev-reviewStaged code reviewer: Noul risk matrix → file profiles → evidence selection → severity → routingShips a local dashboard
awlevin/typesafe-computer-usemacOS computer use via OCR + Jev action choice. A writing model only for free text$0.0002 per decision vs Opus 5 at $0.032
DevMortimer/pi-wardenAgent guardrails that steer instead of interrupting: rules, slop, stuck loops, done claims, irreversible calls6 rule breaks without it, 0 with it across 150 paired runs
AnshChoudhary/typesafe-ai-firewallPre-execution firewall for agent tool calls: one Noul per hazard, ALLOW/APPROVE/BLOCK decided in code0% of hard negatives blocked, vs 39.2% with one "is this dangerous?" question
realZachi/pg-jevNatural-language WHERE clauses for PostgreSQL. No index, no embeddings, no vector column129 rows in ≈1 s for ≈$0.0009; re-thresholding is free
Gaurav-Gosain/jev-sec-benchBlind security benchmarks on public corpora: prompt injection and vulnerable code96.5% injection accuracy, ECE 0.0588, 662 samples
kiarina/labs: safety judgmentModeration vs the OpenAI Moderation API, plus shell-command safety checks before executionJapanese moderation: 36 misses vs OpenAI's 292 of 826 harmful texts
anessbelbati/jev-rerank-benchJev vs Cohere Rerank 4 vs ZeroEntropy across 14 datasets, every raw response savednDCG@10 0.692 vs Cohere 0.691 - reported as a tie
RomanSlack/jev-droneCamera-only quadrotor. Jev is advisory at 2.5 Hz; code owns safety at 50 Hz~110 calls per 65 s flight
TokenTrim/jev-agent-failure-benchmarkCan a decision model find what broke an agent as well as a frontier LLM?Beat GPT-5.4 on every axis, 6,257 traces, $1.28 total
youkiti/tiab-review-pluginTitle and abstract screening for systematic reviews across six labeled medical datasets95.0% recall on 16,645 records at threshold 0.3
zephel01/Jev-sampleThe same decision asked as one 4-option Choice vs four precondition Nouls, with raw logs of 2,320 requests48.3% → 98.3% from question shape alone

Browse by category: Agent supervision · Security · Code tools · Search · Classification · Computer use · Trading · Games and robotics · Domain apps · Open reproductions

No star counts here on purpose. Launch-week stars track attention, not quality - two of the most rigorous projects in this list sit at 1★ while a game demo sits at 200+. Sort by the measurement instead.

Evidence note. Every result above is self-reported by the project author and none has been independently reproduced. All of these are launch-week artifacts built in the first 72 hours. Where a project publishes raw outputs, showcase.md says so - those are the ones worth reading first.


Use-case catalog at a glance

Each category has its own page with the decision shape, evidence, code, and pitfalls.

#Use caseDecision shapeReach for it when
1Routing and triageChoice + ScoreOne known category selects the next code path
2LLM guardrails and verificationNoul + ScoreYou must check an LLM's input, output, or tool call
3Agent harness engineeringChoice + NoulA coding agent needs a fast semantic supervisor
4Search, reranking, and RAGChoice + NoulRelevance decides what reaches the context window
5Structured data extractionChoice over candidatesKnown fields must be recovered from messy text
6Classification at scaleChoiceMillions of rows, bounded labels
7Feature extraction for MLScore + NoulA classical model needs semantic signals
8Real-time loops and gamesChoice per tickDecisions faster than human perception
9Browser and computer useChoice + NoulA screen must become an action
10Domain applicationsAllLegal, finance, insurance, health, recruiting, commerce, moderation
11Frontier and funAllThe demos that show what the primitive can do

Want the raw inventory of everything the community has shipped? See reference/showcase.md for the application showcase, or reference/ecosystem.md for the full census including SDKs and infrastructure.


The one-paragraph summary of how to use Jev well

Keep control flow in code and give the model narrow, atomic judgments. Decompose a broad question into several literal ones and recombine their probabilities with weights you own. Send only the state a question needs, because accuracy falls as irrelevant detail grows. Ask everything you might need in one call, then let code discard what was irrelevant. Gate actions on confidence, scaled to what being wrong costs. Do not ask Jev to count, do arithmetic, compare dates, or generate text. And test the thresholds on your own traffic before you trust them, because the calibration claim is asserted by the vendor and not yet independently reproduced.

The rest of this repo is the long version of that paragraph.


Ground rules for this list

  • Evidence over vibes. Every project entry states what was measured and who measured it. Vendor-reported numbers are labeled as such.
  • Use cases must use Jev. A generic classifier that merely resembles the pattern is not included.
  • Launch-week artifacts are labeled. Many projects were built in the first 72 hours. Treat them as proofs of concept, not production case studies.
  • Corrections welcome. See CONTRIBUTING.md. If a number here is wrong or stale, open a PR.

License

MIT. Not affiliated with or endorsed by TypeSafe AI.