Jev for beginners: how to use it and what to build

<p>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.</p><p><br></p><p><strong>What you’ll learn:</strong></p><ol><li>What makes Jev fundamentally different from every other model I’ve used</li><li>How I analyzed 1,700 PRs for 9 cents and what I found out about where my engineering effort actually went</li><li>The personal meta-analysis you can run on your own Claude and Codex sessions right now</li><li>Why I stopped using Jev alone, and what I pair it with now</li><li>How I turned 4,500 YouTube comments into a searchable audience dashboard for almost nothing</li><li>The real-time app I built in an afternoon that shows something surprising about Jev’s speed</li><li>Why Jev’s pricing model is different from any LLM I’ve used, and what it makes practical to build</li><li>The ChatPRD product insights project: 1,100 signals, 200,000 classifications, and what it cost me</li></ol><p>—</p><p><strong>Brought to you by:</strong></p><p><a href="https://openart.ai/suite/chat?utm_source=online&utm_medium=influencer&utm_campaign=infl-howiai-ga2-na-acq-web"><strong>OpenArt</strong></a>—An all-in-one AI creation platform for images, videos, music, audio, and more</p><p>—</p><p><strong>In this episode, we cover:</strong></p><p>(00:00) Jev launch and what makes it different from every other model</p><p>(02:49) Type-safe values explained</p><p>(05:28) Understanding Jev outputs</p><p>(07:39) Use case 1: PR categorization and pairwise clustering</p><p>(11:12) Use case 2: analyzing your own local Claude Code and Codex sessions</p><p>(13:00) Use case 3: Gmail triage with Jev scoring and LLM follow-up</p><p>(14:30) Use case 4: ChatPRD’s product insights graph</p><p>(18:17) Demo: How I AI audience signal dashboard</p><p>(22:14) Demo: voice-to-color emotion-mapping app</p><p>(25:16) Jev week recap and what’s coming in episode 2</p><p>—</p><p><strong>Tools referenced:</strong></p><p>• Jev (TypeSafe AI): <a href="https://typesafe.ai/">https://typesafe.ai</a></p><p>• Vercel: <a href="https://vercel.com/ai">https://vercel.com/ai</a></p><p>• GitHub API: <a href="https://docs.github.com/en/rest">https://docs.github.com/en/rest</a></p><p>• YouTube Data API v3: <a href="https://developers.google.com/youtube/v3">https://developers.google.com/youtube/v3</a></p><p>• OpenAI Realtime Voice API: <a href="https://platform.openai.com/docs/guides/realtime">https://platform.openai.com/docs/guides/realtime</a></p><p>• Gemini 3.5 Flash-Lite: <a href="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</a></p><p>• API Ninjas Quotes API: <a href="https://api-ninjas.com/api/quotes">https://api-ninjas.com/api/quotes</a></p><p>—</p><p><strong>Where to find Claire Vo:</strong></p><p>ChatPRD: <a href="https://www.chatprd.ai/">https://www.chatprd.ai/</a></p><p>Website: <a href="https://clairevo.com/">https://clairevo.com/</a></p><p>LinkedIn: <a href="https://www.linkedin.com/in/clairevo/">https://www.linkedin.com/in/clairevo/</a></p><p>X: <a href="https://x.com/clairevo">https://x.com/clairevo</a></p><p>—</p><p>Production and marketing by <a href="https://penname.co/">https://penname.co/</a>. For inquiries about sponsoring the podcast, email jordan@penname.co.</p>