TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.

YouTube video by AI Engineer

You can expect a salary of $150,000 - $210,000

Build type-safe JSON REST APIs and clients using Mastro and TypeScript. - mastrojs/api

You can expect a salary of $160,000 - $210,850

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

AI decision models from OpenAI, TypeSafe and Liquid AI are turning classification, routing and confidence scores into a new software battleground, with major implications for accuracy, calibration and accountability.

An experiment with semantic code linting using Jev from TypeSafe AI - schalkneethling/jev-lint

We explored whether TypeSafe AI's Jev can handle complex cloud security and IAM role selection while overcoming traditional LLM drawbacks.

Connect a Python script to the Jev model with the TypeSafe SDK and OpenRouter, then replace brittle input checks with Noul, Score, and Choice answers.

LangChain, 5 Nov 2026. Sourced to github.com.

12,000 Shopify product categories can be searched without a beam search, Raymond Weitekamp of OpenProse told AI Engineer. Weitekamp said the trick is recursive decision models. A parent decision calls a child decision up to a depth limit, with context held outside the model in code. He described TypeSafe Jev as the System One counterpart to generative models, because Jev cannot generate text and only ranks options while code makes the decision. Two coupled Jev compositions played Doom, Weitekamp said. One handled moment to moment shooting choices such as hold, carry, walk or dodge. The other handled map aware exploration, and together they completed levels with no language model in the loop. He showed the same pattern in Factorio. The system scanned production lines, isolated the failing inserter group and dispatched a fix, all as many small ranked choices. His three rules were that context stays outside, a decision can call another decision, and the tree must first work with zero generative calls before it is allowed to compose with models or agents. Tool use arrived fast. People built Jev routers, compaction judges and tool gate checks within 24 hours of access, Weitekamp said. The constraint is enumeration, since someone...

Learn your codebases through self-quizzing and study. Track your knowledge coverage over time. - arjunpatel7/shikhu

TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.