Jev for beginners: how to use it and what to build
- ID
- 29292
- Status
- summarized
- Published
- 28 Sep 2026, 8:03 PM
- Fetched
- 28 Sep 2026, 9:35 PM
- Provider
- Lenny's Newsletter
- Category
- product-startup
- Original URL
- https://www.lennysnewsletter.com/p/jev-for-beginners-how-to-use-it-and
- Source URL
- https://www.lennysnewsletter.com/feed
Summary
- Score
- 6.5
- Created
- 28 Sep 2026, 9:35 PM
- Tags
- Audience
- developersai_ml_learnersai_agent_userssaas_founders
What happened
Claire Vo walks through Jev, TypeSafe AI's "decision model" that returns type-safe structured values (a choice, a score, a probability) instead of generated text, priced at 4 cents per million input tokens with no output charge. She reports running it on five projects in a week: categorizing 1,700 PRs for 9 cents, a meta-analysis of her own Claude and Codex sessions, Gmail triage, the ChatPRD product insights graph (1,100 signals, 200,000 classifications), and a live dashboard built from 4,500 YouTube comments. She also says she stopped using Jev alone and now pairs it with other models such as Gemini 3.5 Flash-Lite.
Why it matters
If your pipeline spends money on an LLM just to bucket, label, or score things, this is a concrete alternative pricing shape to test: input-only billing with no output charge, claimed at 4 cents per million input tokens and 9 cents for 1,700 PR categorizations. The practical move is to take one existing classification or triage job you already run and benchmark a structured-output decision model against your current model on cost and label accuracy, rather than assuming general chat-model pricing. Note this is a launch-week episode with a sponsor segment, so the numbers are the author's own reported results, not an independent benchmark, and there is no Malaysia or Southeast Asia angle in the text.
Discussion angle
Take one classification job your team already pays for - support ticket triage, PR labelling, feedback tagging - and work out what 200,000 classifications would cost on your current model versus an input-only structured-output model. What would you actually build if classification were near-free?