AI Summary
5 min readJev Is Here: A New Kind of AI Decision Engine
The demo that opens this episode is hard to ignore. Ryan Vogel, a member of the founding team at Open Code, loaded 1,700 emails into a Jev classifier — each email with subject, body, sender, and metadata — and asked it to categorize them by type (shopping, work, marketing, finance, security), assign a priority level, score them for spam likelihood, and estimate how urgently each warranted a reply. The whole batch processed in seconds. The total cost: 18 cents. That single number — 4.2 million input tokens and 500,000 output tokens for less than a quarter — is the episode's anchor. It forces a rethinking of what AI can do when speed and price are no longer bottlenecks.
What Jev Actually Is
Jev is not a language model in the familiar sense. It does not generate text, hold conversations, or reason out loud. It is a classifier — a decision engine. You give it an input (say, an email object) and a schema that defines the possible outputs (categories, scores, yes/no thresholds). Jev returns probabilities for each option: an email is 90% spam, 80% urgent, 70% worth replying to. The outputs are structured data — numbers and labels — not prose. This makes them immediately usable in code without parsing or cleanup.
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
Never miss an episode of The Startup Ideas Podcast
Get every new episode summarized in your inbox — free, ~5 minutes to read.
No spam. Unsubscribe anytime.
What you'll learn
- 1 (00:00) **Introduction - What Jev Is and Why It Matters** - The host sets up the episode: Jev is a new type of AI created by Diogo Almeida, and guest Ryan from Open Code will explain it.
- 2 (02:16) **The Core Concept: Jev as a Decision Model** - Ryan explains Jev is not a text-generating LLM, but a classifier that outputs structured data.
- 3 (03:03) **Live Demo: Classifying 1,700 Emails in Seconds for 18 Cents** - Ryan runs a real demo showing Jev categorizing, scoring, and prioritizing a full inbox.
- 4 (07:27) **Mental Model: "AI Decision Maker" vs. "AI Assistant"** - The host and Ryan refine the mental model for using Jev.
- 5 (09:06) **Why You Don't "Ask" Jev - It's a Structured API, Not a Chatbot** - Ryan explains the technical distinction: Jev is an API that returns type-safe data objects, not conversational text.
- 6 (13:35) **Creative Experiment: Can Jev Generate Text by Making "Letter Decisions"?** - Ryan tests if Jev can type out responses by treating each letter as a decision.
- 7 (15:46) **Who Should Use Jev: Low Barrier to Entry for Side Hustles** - Ryan explains Jev is ideal for solo founders and small businesses because it's extremely cheap.
+ Full timestamped outline available in the app
Show Notes
In this episode, I talk with Ryan Vogel about Jev, a new type of AI built for classification. Ryan shows how Jev takes an input plus an output schema and returns a probability for each choice in about 200 milliseconds. He demos Jev sorting 1,700 emails for 18 cents total, then covers lead scoring, support routing, video clipping, and browser control. I push him on the startup angle: find a business with an expensive queue of incoming information and put Jev at the front of it. You leave with a clear mental model, real use cases, and a simple way to try it today.
Links Mentioned:
Jev/Typeface AI: https://typesafe.ai
AI Gateway: https://vercel.com/ai-gateway
Timestamps
00:00 – Intro
02:27 – What Jev Is and Why It Matters
04:32 – Email Triage Demo
07:19 – Jev as an AI Decision Maker
15:46 – How to Use Jev in a Business
20:48 – Startup Idea: Local Services Matching and Instant Quotes
22:51 – Use Case 1: Bitcoin Signal Test and Limits
24:03 – Use Case 2: Auto-Clipping Long Videos
25:27 – Use Case 3: Browser Control: Flight Pick in 7.1 Seconds
26:18 – How to Get Access
27:25 – Closing Thoughts
Key Points
- Jev is a classifier: an input and an output schema go in, and a probability for each choice comes out.
- Ryan's demo scores 1,700 emails for 18 cents total.
- Each Jev query takes about 200 milliseconds, whatever the input and output structure.
- Use Jev at any point where a business makes fast, repeatable decisions on incoming data.
- Keep Jev in an advisory role, and save frontier models for high-intelligence tasks like trading.
- Instant access runs through the Vercel Gateway, and a waitlist covers direct access.
The #1 tool to find startup ideas/trends - https://www.ideabrowser.com
LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products