shipwithjev

Resources

105 builds · page 3 of 3

  1. 0522

    Valid Schema, Wrong Content: Using Jev to Guard a Google ADK Agent

    for a short video, four segments, each tagged with type, duration, and text. The `noul` confidence scores are real Jev API results for the original Traditional Chinese text (an…

    dev.to · Tools & apps

  2. 0521

    TypeSafe Jev vs Claude Code: 4 Models, 2 Real Jobs

    Jev is a model that answers typed questions instead of generating text: yes/no, pick-one, or a score on a scale, each returned as a calibrated probability. You can get the same…

    primeline.cc · Tools & apps

  3. 0519

    system1-mcp v0.1.1

    Jev-powered System 1 reflex engine for AI agents via Model Context Protocol (MCP) ... - Documentation: https://github.com/ericmaddox/system1-mcp#readme - Homepage:…

    pypi.org · Tools & apps

  4. 0518

    Semantic code search without a vector index

    Pass two hands that shortlist to Jev, TypeSafe's decision model, in a single batched call. Jev isn't a chat model, it's what they call a System One model: it doesn't generate…

    dev.to · Tools & apps

  5. 0517

    Semantic code linting with System One models

    A semantic lint is a rule you can state in a sentence but cannot express in a regular linter. Jev turns each rule into a yes/no question over one diff hunk and returns a…

    systemonemodels.org · Tools & apps

  6. 0516

    pi-typesafe-router

    Opt-in Jev task routing for Pi with TypeSafe, Cloudflare, Vercel, and OpenRouter backends and ordered preflight model fallbacks ... Install `pi-types ... -router` from npm and Pi…

    pi.dev · Tools & apps

  7. 0515

    pi-jev-model-router

    Route pi prompts to task-appropriate model tiers with TypeSafe Jev typed judgments. Budget-aware, with automatic fallback. ... Install `pi-jev-model-router` from npm and Pi will…

    pi.dev · Tools & apps

  8. 0514

    MCP Optimization: ลด round-trip ของ resolver ด้วย Jev (ตอนที่ 3)

    นี่คือจุดที่ Jev เข้ามา จากตอน 1-2 เรารู้แล้วว่ามันเป็น "โมเดลตัดสินใจ" ที่เร็วและถูก - ให้ตัวเลือกกับคำถาม มันคืน คำตอบเดียว + ความมั่นใจ (confidence) ไม่ต้อง generate…

    marketdx.hashnode.dev · Tools & apps

  9. 0513

    Jev: Typed decisions for enterprise AI - Michał Chromiak's blog

    Jev is TypeSafe AI's model for that narrower job. You give it the relevant text and define the possible kinds of answer. It returns typed values and probability distributions…

    mchromiak.github.io · Tools & apps

  10. 0512

    Jev in SuperQode: a harness for your code and workflows with Jev agent

    SuperQode is our terminal-first harness for coding agents. You bring a model or an agent. SuperQode owns the loop: tools, permissions, YAML exec-policy, Git Guard, session…

    medium.com · Tools & apps

  11. 0510

    Jev Beat GPT Luna by 1 Point. GPT-6 and Claude Wrote the Answer ...

    Two public sources now say Jev beats GPT-5.6 Luna. Vercel's CEO says so for the safety reviewer in fx, a Vercel tool whose default auto mode runs that reviewer on every command.…

    dev.to · Tools & apps

  12. 0509

    Jev + SystemOne Tune in SuperQode (GEPA): teach decisions from unlabeled examples

    We shipped the SystemOne harness for Jev-like models a few days ago. As soon as we got access to Jev we put progressive tool discovery into the harness: deferred optional tool…

    medium.com · Tools & apps

  13. 0508

    Jev + Pi: a probability gate for my coding agent's shell commands

    TypeSafe released Jev on 2026-09-15. It is a decision-only model: you give it yes/no propositions and it returns a probability instead of text. I put it in front of Pi's `bash`,…

    dev.to · Tools & apps

  14. 0507

    Exploring Jev for AI-Driven QA with agent-device

    # Exploring Jev for AI-Driven QA with agent-device ... TypeSafe recently released Jev, a model for making fast, structured decisions. The company reports response times of 70 to…

    callstack.com · Tools & apps

  15. 0506

    Eval agent responses with Jev - Blog - Braintrust

    Jev handles narrow, typed decisions over unstructured data through TypeSafe's System One API. Your code supplies the relevant state and one or more questions with constrained…

    braintrust.dev · Tools & apps

  16. 0505

    Cutting MCP Round-Trips with Jev (Part 3)

    That's where Jev comes in. From Parts 1-2 we know it's a fast, cheap "decision model": give it options and a question, and it returns one answer plus a confidence score - no long…

    marketdx.hashnode.dev · Tools & apps

  17. 0504

    Code Enumerates, Jev Judges: Building slopcheck on a Model That Never Writes a Word |…

    I built a CI tool this week that reads every pull request and says whether it is AI slop. It flags speculative abstractions, tests that only assert on mocks, swallowed errors,…

    tjklug.com · Tools & apps

  18. 0503

    Can Jev Be a Better Agent Evaluator?

    - Jev is a fundamentally different kind of evaluator. It returns typed answers directly instead of generating text like an LLM judge. - Jev was dramatically more consistent on…

    langchain.com · Tools & apps

  19. 0502

    Building a Prompt Oscilloscope. AI coding agents can inspect…

    The project combines TypeSafe Jev, GitHub Copilot CLI over the Agent Client Protocol (ACP), and a native VS Code chat participant. Together, they create a diagnostic layer for…

    medium.com · Tools & apps

  20. 0501

    Agents Make Three Decisions All Day: 18 JEV Use Cases and When Not to Use It

    Eric Kang Posted on Sep 20 # Agents Make Three Decisions All Day: 18 JEV Use Cases and When Not to Use It A production agent makes the same three kinds of calls all day: pick one…

    dev.to · Tools & apps

  21. 0500

    Jev: AI Decisions as a Typed Function Call | StackToHeap

    # Jev: AI Decisions as a Typed Function Call What I learned using TypeSafe's Jev for code review, and why its more surprising uses are browser control and generative UI.…

    stacktoheap.com · Agents & browsers

  22. 0454

    jev-scout golden-set study

    Hand-labeled 25-item search-triage study with pinned rubric versions and a drift baseline; reports 88% relevance and 96% credibility with all four misses decomposed.

    accuracy · Research & data

  23. 0278

    Wikiracing

    Get from one Wikipedia page to another by picking links.

    TypeSafe AI · Games & real time

  24. 0271

    Every’s editorial vibe check

    37 documents, 21 questions each, 1,709 judgments for under a cent.

    @danshipper · Content & growth · <$0.01

  25. 0270

    Jev plays chess

    Jev picks from the legal moves, compared with reasoning models.

    Maxim Saplin · Games & real time