X post · by Malek Ould-Oulhadj

Support answers in a Mac app

Jev reads the built-in manual and picks the article that answers the user.

Malek Ould-Oulhadj

@malekoo

First @typesafeai use case, live in our Mac app: setup and troubleshooting help when no model is loaded. Model downloading, load failed, API returning 503, phone won't pair: the user asks, Jev reads the question with the whole built-in manual as state and decides, with probabilities, what it is and which article answers it, or that nothing does. The app then shows the real documentation and live status. Jev decides, the app answers from its own docs. No model loaded, nothing invented. 42/42 on a held-out set: paraphrases, typos, French, German, Spanish, features that don't exist, follow-ups. Median 0.93 s. Great breakthrough by the TypeSafe team. Thank you.

Sep 17, 2026 · 5 likesOpen on X

Malek Ould-Oulhadj shipped Jev in a Mac app for setup and troubleshooting help when no model is loaded. Jev reads the question with the whole built-in manual as state, and decides what the problem is and which article answers it, or that none does. The app then shows its own documentation, so nothing is invented. He reports 42 of 42 correct on a held-out set, with a median of 0.93 seconds.

Open the source

500 emails for 3.5 cents

Emails: 500
Cost: 3.5 cents

vogel

@ryanvogel

this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away

X postTriage and routing

Triage across 1,500 emails

Volume: ~1,500 emails

Hassan

@nutlope

Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure. 31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy. The full run took 16 seconds & ~$0.07 in inference costs: - $0.068 from Kimi K3 on @togethercompute - $0.003 (1/3 of a cent) from Jev on @typesafeai. I think this is a really interesting pattern: use a fast specialized model like Jev for the narrow task, then route the uncertain cases to a larger LLM. I feel like this kind of approach could be a game changer for use cases like fraud or anything realtime. You can use the speed & low cost of Jev while having a larger LLM as a fallback to ensure high accuracy.