Playground
CommunityJev Demos & Experiments
Try Jev AI Playground
An independent playground for TypeSafe's Jev with clearly labeled modes: load Choice, Noul or Score examples for support routing, urgency and frustration, or run live calls against the real API when the page says live access is available.
- Format
- Playground
- Reading time
- 2 min
- Published by
- Community
- Last verified
- Oct 2026
- Platforms
- Browser
Highlights
- Live Jev calls the real API; Interactive Demo and illustrative outputs are explicitly labeled as not live.
- Covers all three primitives: Choice with a full distribution, Noul yes/no probability, and rubric Score.
- Presets include support routing, tool selection, risk review, loop control, urgency and frustration scoring.
- Says plainly it is an independent resource, not affiliated with or operated by TypeSafe AI.
- Links its own experiments: a fact-checking test and a 48-case scheduling test where context beat the Jev layer.
Watch out
Grounded in the tryjevai.com page captured on 2026-10-15; the availability check had not resolved in the capture, and the page itself flags illustrative demo outputs as not measuring Jev, so treat every number shown in demo mode as an example rather than a result.
Questions about this entry
Short answers drawn from the linked project or page.
An independent web playground for TypeSafe's Jev: load an example, pick Choice, Noul or Score, and see the request and response shapes; when live access is available it calls the real Jev API.
The page labels its mode: Live Jev calls the real API, while Interactive Demo and illustrative outputs—such as the 96% Billing example—are presets that do not measure Jev or its speed.
Choice picks one option and returns the full probability distribution; Noul asks a yes/no question and returns the probability that the answer is yes; Score rates a state against an ordered rubric and returns a probability-weighted score.
Scheduling confirmation, routing a duplicate-charge message to billing or support, judging whether a checkout outage needs urgent attention, three-level customer frustration, agent tool selection and agent loop decisions.
No, and the page says so plainly: it is an independent resource, not affiliated with or operated by TypeSafe AI, so its demonstrations and guides should be read as one developer's work.
The captured page does not ask visitors for a key: live runs call Jev server-side, and when live access is unavailable the playground labels the mode and falls back to labeled demo mode.
Yes. It links hands-on tests including a fact-checking experiment with results, costs and a miss, and a three-arm scheduling test where, across 48 synthetic cases, better context beat adding a Jev decision layer.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Show HN: Ad Spend Guard gates budget before the auction, not the creative after.
Show HN: Gating ad budget with a decision modelRead the thread on Hacker NewsX: Field Advisory sends marginal readings to an agronomist instead of a spray.
This post couldn't be loaded here — read it on X.https://x.com/agriwisehq/status/2781000000000000003More Jev resources like this
A live, graphical dojo for Jev with six real-time canvas scenes over one WebSocket: task routing across model tiers, ticket triage, inbox-scale queues and an honest Jev-vs-Claude gauntlet. Boots in SIM mode without an API key.
Jev Demos & Experiments#community#catalog-import#madewithjev
An independent lab for trying the Jev model: a customer-message example plus experiments for task routing, context selection and evidence checks. It shows choice, score and boolean answers with probabilities and can export the request as TypeScript.
Jev Demos & ExperimentsPlayground#community#catalog-import#yibie
Community
An independent browser playground that runs TypeSafe Jev on one question or several, with ready examples for routing, refunds, urgency, and the next agent action.
Jev Demos & ExperimentsPlayground#community#playground#tutorial
Community
E-commerce customer-service quality sandbox: Jev judges intent, emotion, urgency and risk per message, an 8-rule decision table routes to queues with SLAs, and dangerous agent phrasing is blocked with rewrite suggestions before it is sent.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
kiler398/jev-demoTypeScript
kiler398/jev-demoTypeScriptA BYOK workbench for practicing Jev concepts without official access: emulates State, Noul, Score and Choice via Groq, OpenAI, Anthropic, Gemini or local Ollama, or runs against native Jev with authorized credentials.
Jev Demos & Experiments#community#catalog-import#logicrw
A Next.js workbench for evaluating AI ticket triage with TypeSafe AI: classify, route and score support tickets through structured schemas, then inspect outputs, latency, token use and estimated cost in a three-column view.
Jev Demos & Experiments#community#github#typescript
Community
netflix2023/jevTypeScript
netflix2023/jevTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.