All decision model projects
2823 public apps, SDKs, integrations, demos and write-ups built on decision models. Projects with working code come first.
Page 89 of 95
Halv blog post reporting a 57.1% agent cost reduction from putting Jev in the agent loop on SWE-rebench Astra pairs.
ArticlediscussionDev.to article on Jev's founder and a walkthrough of using Jev through the Vercel AI SDK's evaluate integration.
ArticlediscussionTypeScriptLatent Space podcast episode with TypeSafe's Diogo Almeida on RLCD, intelligence per dollar, reliability and post-chat interfaces.
ArticlediscussionBlog post by Alex Molas with an HN thread arguing statistically that Jev's calibration claim cannot hold, with methods written out.
ArticlediscussionBlog post building the smallest working Jev-style decision loop in 25 lines of Python, with a busy HN debate.
ArticlediscussionPythonTenuo blog post pairing the typed-decision loop with scoped authority so confidence only authorises what scope already allows.
ArticlediscussionSimon Willison's blog post on what changes when a model's output is a typed decision instead of prose.
ArticlediscussionSubstack essay arguing cheap calibrated decisions will shift where AI inference spending goes.
ArticlediscussionBlog post that plays poker with Jev to probe where a fast decision model helps and where it falls short.
ArticlediscussionVercel's decision guide on when to use a System One model like Jev versus a frontier model like GPT-6 Astra.
ArticlediscussionJapanese Zenn article by mizchi pitting Jev against itself at gomoku, with source code and timing logs.
ArticlediscussionThe Neuron's explainer article on TypeSafe's Jev and System One models: AI decisions without a chatbot.
ArticlediscussionAnthony Maio's Substack essay on what a model that cannot generate text is for, with a critical look at Jev's claims.
ArticlediscussionDataCamp blog overview of Jev and System One models covering the primitives, pricing and TypeSafe's workflow evaluations.
ArticlediscussionTypeSafe's manifesto arguing for machine-native intelligence built for software rather than conversation.
ArticlediscussionEvery Vibe Check article: Mike Taylor runs a writing corpus through TypeSafe's Jev and reports how it judged it.
ArticlediscussionInfoWorld article (2026-09-17) on TypeSafe's models for machines, listing decisions like which tool to invoke or whether to approve.
ArticlediscussionCollector note confirming TypeSafe's docs index (llms.txt) still lists 30 articles and 18 cookbooks, with no new pages.
ArticlediscussionBlog post that replaces an agent's classification loop with a single Jev call and reports the loop running 7x faster.
ArticlediscussionIndependent article walking through Jev and separating TypeSafe's published claims from public evidence.
ArticlediscussionNews note that TypeSafe added a Team page and an Enterprise navigation entry, read as a commercialization signal.
ArticlediscussionThe Register's launch coverage of TypeSafe AI and Jev, including the Doom demo and the $40M seed round.
ArticlediscussionFinancial Times report that TypeSafe drew funding approaches that could value it at $10bn or more after Jev launched.
ArticlediscussionForkast news analysis arguing that Jev's refusal to generate text is the feature, and what that means for inference spend.
ArticlediscussionDevelopers Digest release-week roundup of Jev covering the API, evals, an adapter and the agent skill.
ArticlediscussionBlog experiment making text-only Jev guess what a sketch shows from a text description of the drawing.
ArticlediscussionJapanese article testing whether LLMs can replicate Jev, via a logit shortcut on Gemma and the Mario harness.
ArticlediscussionNews report that Jev drew record paid-developer interest on Vercel and tripled OpenRouter token volume in one weekend.
ArticlediscussionIndependent benchmark of Jev versus four LLMs on Banking77 routing and prompt injection, plus a gated cascade.
ArticlediscussionShort practical introduction to Jev with a Python ticket-triage example.
ArticlediscussionPython