Case wall
Jev AI examples, page 4
407 real Jev AI builds and public demos, updated daily. Original text, metrics, and a link back to each source.
Last updated
Public Jev AI examples and demos, not official TypeSafe docs. Clients and SDKs are in the Jev GitHub projects. Paths for jev-latest, Vercel, and OpenRouter are in the September 2026 channel map.
Agent-skill repositories are listed on Jev skills on GitHub.
OpenRouter model ids recorded for Jev AI are on Jev AI on OpenRouter. Rubric and eval posts are on Jev as a judge. How the company and the model fit together is on TypeSafe AI. The pricing calculator uses the published input rate.
No posts match these filters.
@a_latner benchmarks three-day-old Jev image classification against Haiku 5.5 on real production data and reports matching quality.
@typesafeai Jev image classification is 3 days old. I benchmarked it against Haiku 5.5 on real production data. We know it's faster, but are the results as good…
@huuw_khoa benchmarks Jev against Gemma 4 12B and gpt-oss-20b on 60 knowledge-graph questions in open-source hopwise.
Can a model built for typed decisions walk a knowledge graph better than a general LLM? I tried Jev, Gemma 4 12B and gpt-oss-20b on 60 questions. Feedback and i…
@jessethanley screens PostShiba sign-ups after hours with Exa plus TypeSafe Jev to keep abuse down while still letting real companies in.
So we've opened up sign-ups to PostShiba outside of biz hours and to keep abuse down I've added a screening that uses a combo of @ExaAILabs and @typesafeai Jev…
@heyona_ai shipped Ask Ona Pro cards: type a to-do, recurring task, or meeting and Jev turns the bar into an add-ready card.
Ask Ona now does what you type. Type a to-do, a recurring task or a meeting, and the bar turns into a ready card. Enter adds it. Esc asks Ona instead. Live for…
@odinachidavid shipped JevChess: 3D browser chess vs TypeSafe Jev (Beginner/Pro/Legendary), free, open source.
I built JevChess ♞: realistic 3D chess in your browser vs Jev, @typesafeai's decision model. Beginner, Pro or Legendary. Works on your phone. Free, no sign-up.…
@Adityakuma8784 built jev-harness to test coding-agent guardrails; a typical hook let 331 of 503 disguised dangerous commands through.
Your AI coding agent has guardrails: hooks, permission rules, CLAUDE.md, AI reviewers. Almost nobody tests them. I built jev-harness to test them. Against a typ…
@MalayVasa built text-to-screenshot: say what you want and a crosshair grabs it, powered by Jev 1.14.
text-to-screenshot just say what you want and the crosshair goes and gets it. built with jev 1.14 from @typesafeai
@UnslothAI released a free notebook to train your own decision model so Qwen3.5-4B answers decisions instead of text on 8GB VRAM locally.
You can now train your own Decision model with our free notebook! 💡 Qwen3.5-4B will generate decisions instead of text on just 8GB VRAM locally. Learn to data p…
@pablositooo open-sources Last Shelter, a 3D defense game where Jev classifies and code decides; 0 humans shot in sims.
I built Last Shelter, a 3D defense game, with Claude Opus 5.5. An AI ( JEV by @TypeSafeAI ) classifies, the code decides. 0 humans shot across thousands of simu…
@_vMyth’s jevals runs agent evals and guardrails as one Jev decision request per trace, cheap enough to score every run.
Runs agent evals and guardrails as 1 request to a Jev decision model, not an LLM judge. Cheap enough to score every trace. Change 2 defaults: the quick-start se…
@TripoliEnzo shipped a free open-source visual builder for TypeSafe Jev: compose Choice/Score/Noul, export JSON/cURL/TS for /v1/systemone.
I built a free, open-source builder for @typesafeai ‘s Jev. Compose Choice / Score / Noul questions visually, add {{parameters}}, get the exact JSON for /v1/sys…
@Asteri_eth listed ten GitHub repos already shipping on Jev, from a browser agent to a Claude Code bridge and a LangGraph router.
People are already shipping a browser agent, a Claude Code bridge and a LangGraph router on top of Jev. Here are all 10 repos. Got API access and no idea where…
@thepericulum says the GC AI eng team ran a one-day hackathon with TypeSafe Jev and produced 38 projects/experiments, sharing demos in a thread.
Last week the GC AI eng team paused work for the day to do a hackathon seeing what we can build with @typesafeai Jev 38 projects and experiments later, here are…
@_avichawla explains standard RAG (chunk → embed → retrieve → optional rerank → LLM) versus adding Jev into the RAG path, with an animated explainer video.
RAG vs. Jev + RAG, clearly explained! In a standard RAG setup, documents are split into chunks, converted into embeddings, and stored in a vector DB. When a que…
Quoted @_avichawla
@OpenRouter posted Decision Model Rankings for spend share and token share by model and task type, and says @typesafeai is leading all categories today.
New: Decision Model Rankings! See the spend share and token share of different decision models and task types, including Relevance, Correctness, Instruction Fol…
@Sumanth_077 built a data-analyst agent where Qwen writes SQL/answers and Jev reviews question clarity, SQL fit, and grounded explanations; open-sourced under Hands-On-AI-Engineering.
I built a data analyst agent with Jev as the review layer! Qwen handles the main agent work, Jev acts as the review layer, and Vercel eve runs the agent loop, t…
Quoted @Sumanth_077
@h_nilforoshan benchmarked the OpenAI Decisions API against Jev for HiringCafe.com: relevance of a query or resume to a job, scored 1-10. The post says OpenAI costs 2x more and is 5-10% worse.
I benchmarked "Jev-killer" OpenAI Decisions API against Jev for https://HiringCafe.com, serving 2.5 million users. The task is to predict how relevant a user qu…
Quoted @OpenAIDevs
@caseytraina built a macOS Spotlight replacement with Jev that searches apps and can run actions across apps.
Apple spotlight search has been broken for months now so I built a new one using Jev Not only does it work for application search but it can also perform any ac…
@soderlind built Jev Mail Triage for Proton Mail: local spam and phishing checks via Proton Bridge, dry-run by default.
Less spam. More inbox. 📩 I built Jev Mail Triage for Proton Mail: spam + phishing detection powered by @typesafeai´s Jev through Proton Bridge. Dry-run by defau…
@elbruno released ElBruno.AI.Decisions, one .NET API for Choose, Score & Assess using Microsoft Foundry, local Ollama models, and Jev. Open source at https://github.com/elbruno/ElBruno.AI.Decisions.
Less chat. More decisions. 🎯 ElBruno.AI.Decisions: one .NET API to Choose, Score & Assess with Microsoft Foundry, local Ollama models and Jev. Probabilities, no…
@davert shipped decision-based testing in CodeceptJS so Jev can assert outcomes that are hard to express in code.
In latest release of @CodeceptJS we introduced a new approach of decision-based testing using Jev It is not always possible to express in assertion code the des…
@ValsAI says they independently tested TypeSafe's Jev against 11 other models. On 400 claim-verification questions it matched GPT-6 Astra's 97.5% accuracy at about 1/500th the cost.
Can a model that doesn’t generate text compete with frontier LLMs? We independently tested TypeSafe’s Jev against 11 other models. On 400 claim-verification que…
@k_cieslak built an OpenCode plugin that uses TypeSafe Jev for automatic handoff and routing between harness agents, enabling Plan → Build → Review without human interaction. Repo: https://github.com/Krzysztof-Cieslak/jev-agent-control
I've built a small tool - @opencode plugin using @typesafeai Jev to do automatic handoff and routing between agents available in the harness. It basically enabl…
@eeuhn fine-tuned a legal decision model with Unsloth’s notebook to classify trademarks on the Abercrombie spectrum, hitting 75.8% on LegalBench.
I'm like legal Jev pilled after using Unsloth's train-your-own-Jev model notebook. I made a legal Jev to classify trademarks under the Abercrombie spectrum. Tra…