{"slug": "jev-for-beginners-how-to-use-it-and-what-to-build", "title": "Jev for beginners: how to use it and what to build", "summary": "TypeSafe AI's Jev decision model returns type-safe structured values — a choice, a score, or a probability — instead of generated text, priced at 4 cents per million input tokens with no output charge, according to a hands-on account by Claire Vo. Vo ran Jev on five projects, including categorizing 1,700 pull requests for 9 cents, classifying 200,000 items across 1,100 ChatPRD product signals, and building a live dashboard from 4,500 YouTube comments. Vo said she stopped using Jev alone and now pairs it with other models.", "body_md": "Jev is TypeSafe AI’s new decision model. It returns type-safe structured values (a choice, a score, a probability) instead of generated text, at 4 cents per million input tokens with no output charge. This week I ran it on five real projects: PR categorization, a meta-analysis of my own Claude and Codex sessions, Gmail triage, the ChatPRD product insights graph, and a live audience dashboard built from 4,500 YouTube comments.\n\n**Listen or watch on [YouTube](https://youtu.be/-KIBgpGA_XI), [Spotify](https://open.spotify.com/show/4aRP2XSavdtrLG5FZoonOK), or [Apple Podcasts](https://podcasts.apple.com/us/podcast/how-i-ai/id1809663079)**\n\n### What you’ll learn:\n\n1. What makes Jev fundamentally different from every other model I’ve used\n2. How I analyzed 1,700 PRs for 9 cents and what I found out about where my engineering effort actually went\n3. The personal meta-analysis you can run on your own Claude and Codex sessions right now\n4. Why I stopped using Jev alone, and what I pair it with now\n5. How I turned 4,500 YouTube comments into a searchable audience dashboard for almost nothing\n6. The real-time app I built in an afternoon that shows something surprising about Jev’s speed\n7. Why Jev’s pricing model is different from any LLM I’ve used, and what it makes practical to build\n8. The ChatPRD product insights project: 1,100 signals, 200,000 classifications, and what it cost me\n\n### Brought to you by:\n\n**[OpenArt](https://openart.ai/suite/chat?utm_source=online&utm_medium=influencer&utm_campaign=infl-howiai-ga2-na-acq-web)**—An all-in-one AI creation platform for images, videos, music, audio, and more\n\n### In this episode, we cover:\n\n([00:00](https://www.youtube.com/watch?v=-KIBgpGA_XI)) Jev launch and what makes it different from every other model\n\n([02:49](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=169s)) Type-safe values explained\n\n([05:28](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=328s)) Understanding Jev outputs\n\n([07:39](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=459s)) Use case 1: PR categorization and pairwise clustering\n\n([11:12](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=672s)) Use case 2: analyzing your own local Claude Code and Codex sessions\n\n([13:00](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=780s)) Use case 3: Gmail triage with Jev scoring and LLM follow-up\n\n([14:30](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=870s)) Use case 4: ChatPRD’s product insights graph\n\n([18:17](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=1097s)) Demo: How I AI audience signal dashboard\n\n([22:14](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=1334s)) Demo: voice-to-color emotion-mapping app\n\n([25:16](https://www.youtube.com/watch?v=-KIBgpGA_XI&t=1516s)) Jev week recap and what’s coming in episode 2\n\n### Tools referenced:\n\n• Jev (TypeSafe AI): [https://typesafe.ai](https://typesafe.ai)\n\n• Vercel: [https://vercel.com/ai](https://vercel.com/ai)\n\n• GitHub API: [https://docs.github.com/en/rest](https://docs.github.com/en/rest)\n\n• YouTube Data API v3: [https://developers.google.com/youtube/v3](https://developers.google.com/youtube/v3)\n\n• OpenAI Realtime Voice API: [https://platform.openai.com/docs/guides/realtime](https://platform.openai.com/docs/guides/realtime)\n\n• Gemini 3.5 Flash-Lite: [https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite)\n\n• API Ninjas Quotes API: [https://api-ninjas.com/api/quotes](https://api-ninjas.com/api/quotes)\n\n### Where to find Claire Vo:\n\nChatPRD: [https://www.chatprd.ai/](https://www.chatprd.ai/)\n\nWebsite: [https://clairevo.com/](https://clairevo.com/)\n\nLinkedIn: [https://www.linkedin.com/in/clairevo/](https://www.linkedin.com/in/clairevo/)\n\nProduction and marketing by [https://penname.co/](https://penname.co/). For inquiries about sponsoring the podcast, email [\\[email protected\\]](https://www.lennysnewsletter.com/cdn-cgi/l/email-protection).", "url": "https://wpnews.pro/news/jev-for-beginners-how-to-use-it-and-what-to-build", "canonical_source": "https://www.lennysnewsletter.com/p/jev-for-beginners-how-to-use-it-and", "published_at": "2026-09-28 12:03:04+00:00", "updated_at": "2026-09-28 12:19:07.210594+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "large-language-models", "artificial-intelligence"], "entities": ["Jev", "TypeSafe AI", "Claire Vo", "ChatPRD", "Claude", "Codex", "YouTube", "Vercel"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/jev-for-beginners-how-to-use-it-and-what-to-build", "markdown": "https://wpnews.pro/news/jev-for-beginners-how-to-use-it-and-what-to-build.md", "text": "https://wpnews.pro/news/jev-for-beginners-how-to-use-it-and-what-to-build.txt", "jsonld": "https://wpnews.pro/news/jev-for-beginners-how-to-use-it-and-what-to-build.jsonld"}}