Article
CommunityJev Guides & Articles
The Merge: Jev as intelligence-infused if-statements
An episode of The Merge (by CodeRabbit) recorded at the first Jev hackathon 11 days after launch; TypeSafe DevRel Allie Laabs explains how Jev replaces prompt-parse cycles with typed choice, score and yes/no outputs.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Author
- Hendrik Krack
- Last verified
- Oct 2026
Used inJev for Software & DevTools
Highlights
- Recorded at CodeRabbit HQ in San Francisco during the first Jev hackathon, run by TypeSafe and the AI Collective, 11 days after launch.
- Laabs: instead of turning program state into a prompt and parsing text back, Jev returns a choice, a score, or a yes/no probability, with nothing to parse.
- Topics include spotting Jev-shaped problems in your app, speculative prompting in one call, and generative UI from the hackathon.
- Laabs calls Jev the intelligence per dollar and says making it as cheap as possible is a cornerstone because that enables everybody to use it.
- She describes Jev as the direct line for machine-to-machine intelligence and says the launch was larger than the team could have anticipated.
Watch out
Copy reviewed against the Exa Library episode page on 2026-10-17; the transcript preview is truncated, so only the visible excerpt and episode notes are reflected. The guest is TypeSafe's own DevRel explaining her company's product.
Questions about this entry
Short answers drawn from the linked project or page.
At CodeRabbit HQ in San Francisco during the first Jev hackathon, run by TypeSafe and the AI Collective, 11 days after launch. The Merge episode 20 was published October 1, 2026, and runs 31 minutes.
Most apps use LLMs the long way: turn program state into a prompt, get text back, then parse that text into a value the code can branch on. Jev skips the text - you send a state plus typed questions and get back a choice, a score, or a yes/no probability.
Jev's answer arrives as a typed output, so there is no text to interpret, and it cannot answer with an option you did not allow, per the episode notes. The input is a state such as a ticket, a transaction or a tool call.
Classification, routing and 'gut feeling' logic you could not write before, plus generative UI, real-time use cases, and what builders made at the hackathon.
The recommended pattern of asking every question in one call rather than making sequential requests, one of the techniques the episode covers for using Jev well.
The episode notes list a one-sentence correction Laabs gives coding agents when they write Jev code; the visible preview names it as a segment but does not spell the sentence out.
TypeSafe's founding DevRel, who jokes that she is the entire dev rel department - both lead and most junior - and says Jev is meant to be the cheapest possible machine-to-machine intelligence.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Simon Willison's overview of Noul, Choice, and Score, and where a decision model fits.
benwerd53 pointsJev introduces a new shape of LLMRead the thread on Hacker NewsHacker News: swyx posts the Latent Space interview with Diogo Almeida.
swyx4 pointsJev: System One Models for Prod, Not God – With Diogo Almeida, CEO, TypeSafe AIRead the thread on Hacker NewsX: Diogo Almeida in five minutes
X: LLMs vs. Jev, clearly explained
More Jev resources like this
John Lindquist joins Claire Vo to walk through eight Jev use cases, from a real-time voice to-do app to data deduplication with confidence scores, on the episode billed as Jev week at How I AI.
Jev Guides & ArticlesArticle#community#press#podcast
Community
VentureBeat's Sam Witteveen argues a large share of enterprise AI only needs a label, not generated text. Per TypeSafe, Jev returns choices, scores and yes/no answers in 70 to 500 ms at $0.042 per million input tokens, with output tokens free.
Jev Guides & ArticlesArticle#community#press#explainer
Community
On The MAD Podcast, Matt Turck talks with TypeSafe CEO Diogo Almeida about why intelligence per dollar matters more than enterprise adoption, and why RLVR benchmark gains still leave models 95% Einstein, 5% Mr. Bean.
Jev Guides & ArticlesArticle#community#press#podcast
Community
A BIG CHANGE analysis of the Diogo Almeida Latent Space interview: Jev's most consequential proposition is the unit of automation, a bounded judgment inside an existing process, and the launch claim that Jev can't hallucinate needs a narrow reading because schema matching does not establish truth.
Jev Guides & ArticlesArticle#community#press#explainer
Community
TWIML episode 779 features TypeSafe co-founder and CEO Diogo Almeida on Jev, the company's model for bringing fast, reliable intelligence directly into software, and why text-generating models are poorly suited to many real-world automation decisions.
Jev Guides & ArticlesArticle#community#press#podcast
Community
In Law://WhatsNext's return episode, guest Chris Bridges of AI-native law firm Tacit Legal demonstrates Jev returning structured contract answers in 0.3 seconds where a chat model took 9.6 seconds.
Jev Guides & ArticlesArticle#community#press#podcast
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.