Jev入门:用TypeSafe AI做结构化决策与低成本自动化
Jev for beginners: how to use it and what to build
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.
Jev 是 TypeSafe AI 推出的全新决策模型。它返回类型安全的结构化值(如选项、评分或概率),而非生成的文本,每百万输入 token 仅需 4 美分,且无输出费用。本周我在五个真实项目中对其进行了测试:PR 分类、对我自身 Claude 和 Codex 会话的元分析、Gmail 邮件分拣、ChatPRD 产品洞察图谱,以及基于 4,500 条 YouTube 评论构建的实时观众仪表盘。
Listen or watch on YouTube, Spotify, or Apple Podcasts
在 YouTube、Spotify 或 Apple Podcasts 上收听或观看
What you’ll learn:
你将了解到:
- What makes Jev fundamentally different from every other model I’ve used
- How I analyzed 1,700 PRs for 9 cents and what I found out about where my engineering effort actually went
- The personal meta-analysis you can run on your own Claude and Codex sessions right now
- Why I stopped using Jev alone, and what I pair it with now
- How I turned 4,500 YouTube comments into a searchable audience dashboard for almost nothing
- The real-time app I built in an afternoon that shows something surprising about Jev’s speed
- Why Jev’s pricing model is different from any LLM I’ve used, and what it makes practical to build
- The ChatPRD product insights project: 1,100 signals, 200,000 classifications, and what it cost me
- 是什么让 Jev 与我使用过的所有其他模型从根本上不同
- 我是如何以 9 美分的成本分析了 1,700 个 PR,以及我从中发现我的工程精力实际流向何处
- 你可以立即在自己本地的 Claude 和 Codex 会话上运行的个人元分析方法
- 为什么我不再单独使用 Jev,以及我现在将其与什么搭配使用
- 我是如何几乎零成本地将 4,500 条 YouTube 评论转化为可搜索的观众仪表盘的
- 我在一个下午构建的实时应用,展示了关于 Jev 速度的惊人事实
- 为什么 Jev 的定价模式与我使用过的任何 LLM 都不同,以及它使得哪些构建变得切实可行
- ChatPRD 产品洞察项目:1,100 个信号、200,000 次分类及其成本
Brought to you by:
由以下内容赞助播出:
OpenArt—An all-in-one AI creation platform for images, videos, music, audio, and more
OpenArt——集图像、视频、音乐、音频等创作于一体的全能 AI 平台
In this episode, we cover:
在本集中,我们将涵盖:
(00:00) Jev launch and what makes it different from every other model
(00:00) Jev 发布及其与其他模型的根本区别
(02:49) Type-safe values explained
(02:49) 解释类型安全值
(05:28) Understanding Jev outputs
(05:28) 理解 Jev 的输出
(07:39) Use case 1: PR categorization and pairwise clustering
(07:39) 用例 1:PR 分类与成对聚类
(11:12) Use case 2: analyzing your own local Claude Code and Codex sessions
(11:12) 用例 2:分析你本地的 Claude Code 和 Codex 会话
(13:00) Use case 3: Gmail triage with Jev scoring and LLM follow-up
(13:00) 用例 3:结合 Jev 评分与 LLM 后续处理的 Gmail 邮件分拣
(14:30) Use case 4: ChatPRD’s product insights graph
(14:30) 用例 4:ChatPRD 的产品洞察图谱
(18:17) Demo: How I AI audience signal dashboard
(18:17) 演示:我如何构建 AI 观众信号仪表盘
(22:14) Demo: voice-to-color emotion-mapping app
(22:14) 演示:语音转颜色情绪映射应用
(25:16) Jev week recap and what’s coming in episode 2
(25:16) Jev 周回顾及第二集预告
Tools referenced:
引用的工具:
• Jev (TypeSafe AI): https://typesafe.ai
• Jev(TypeSafe AI):https://typesafe.ai
• Vercel: https://vercel.com/ai
• Vercel:https://vercel.com/ai
• GitHub API: https://docs.github.com/en/rest
• GitHub API:https://docs.github.com/en/rest
• YouTube Data API v3: https://developers.google.com/youtube/v3
• YouTube Data API v3:https://developers.google.com/youtube/v3
• OpenAI Realtime Voice API: https://platform.openai.com/docs/guides/realtime
• OpenAI Realtime Voice API:https://platform.openai.com/docs/guides/realtime
• Gemini 3.5 Flash-Lite: https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite
• Gemini 3.5 Flash-Lite:https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite
• API Ninjas Quotes API: https://api-ninjas.com/api/quotes
• API Ninjas Quotes API:https://api-ninjas.com/api/quotes
Where to find Claire Vo:
如何找到 Claire Vo:
ChatPRD: https://www.chatprd.ai/
ChatPRD:https://www.chatprd.ai/
Website: https://clairevo.com/
网站:https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
LinkedIn:https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
X:https://x.com/clairevo
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].
制作与营销由 https://penname.co/. 关于赞助播客的咨询,请发送邮件至 [email protected]。
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力