Article
CommunityJev Guides & Articles
Exa: Law://WhatsNext tests Jev on legal contract review
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.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Author
- Alex and Tom
- Last verified
- Oct 2026
Highlights
- The Exa Library episode is Law://WhatsNext episode 1, published September 29, 2026, running 27 minutes with Chris Bridges as guest.
- Bridges is a partner and COO at Tacit Legal, an AI-native law firm, and the driving force behind its supervised AI contract review service Tilder.
- In a simulated run he says Jev responded in 0.3 seconds with all of the answers, while the chat-based model took 9.6 seconds.
- He describes Jev's output as very structured, down to whether confidentiality is capped and what the cap applies to.
- The episode notes call Jev the first of TypeSafe's System One models; Bridges says System One is a term TypeSafe invented.
Watch out
Copy reviewed against the Exa Library episode page on 2026-10-17. The speed comparison comes from a single simulated demo in a transcript excerpt, and the guest works for a law firm building supervised AI contract review, so he is not a neutral evaluator.
Questions about this entry
Short answers drawn from the linked project or page.
The first episode of the podcast's new season: hosts Alex and Tom bring back guest Chris Bridges to make sense of Jev, what it is, how to access it, and its potential implications for legal work.
A partner and COO at Tacit Legal, an AI-native law firm, and the driving force behind its supervised AI contract review service Tilder. He appears as a returning guest and describes himself as a massive cynic.
In the simulated contract run, Bridges says Jev responded in 0.3 seconds with all of the answers, while the chat-based model took 9.6 seconds and returned an unstructured block of text.
Structured contract points: whether confidentiality is capped (yes), and whether the cap is calculated on fees paid or payable versus a total (fees paid or payable), which the episode contrasts with prose output.
Bridges says it is a completely new term TypeSafe invented, rooting it in an economist's idea of two brains: a fast, instinctive system one and a slower, reasoning system two.
The show notes say it is a hype-free, informative conversation about Jev and its potential relevance to legal products and services, and the guest is described as a massive cynic.
The timing figure comes from one simulated demo rather than an independent benchmark, and the guest works for a firm building legal AI products, as the entry's caveats note.
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
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
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.
Jev Guides & ArticlesArticle#community#press#podcast
Community
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
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
ThursdAI's September 17 episode covers TypeSafe's Jev launch with founding DevRel Allie Laabs: choice, score and null primitives, $42-per-billion input pricing, and a live X timeline classifier running at 12 tweets a second.
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.