Ron Veen·1d agoJev and System One Models: The Decision Layer Your Java Code Has Been MissingCall TypeSafe’s Jev model from plain Java to classify, score, and route support tickets with calibrated probabilities, then branch on…
Daniel Avila·1d agoDrex 2.0 in 10 Minutes: From Sign-Up to Your First Agent DecisionsCreate a Nace account, get an API key, and run a ready-made Jupyter notebook that routes support tickets.A response icon1A response icon1
Serhii Smetanskyi·2d agoTesting LLMs with Jev-Based Evals: Clef as the JudgeLLM-as-judge has three problems that show up as soon as the suite grows. The first is cost. Every test case is a paid call to a large…A response icon1A response icon1
Jihane EL GASMI·Nov 2System One Models vs LLMs: When an LLM Becomes a Decision ModelPart 2 of 4 · Seven LLM-based decision models against the LLM they’re built on
anushika gupta·Nov 1Jev: AI Built for Decisions, Not Conversations.TypeSafe AI’s System One model takes a different approach to AI: fewer generated words, faster structured decisions, and outputs software…
Phillip Wenig·Oct 30System One Time Series ModelsAsk your time series questions, get calibrated answers.A response icon1A response icon1
Ben Tan·Oct 30Revisiting My 3-Tier LLM Guardrail: When the Judge Returns Probabilities Instead of Paragraphs“Just as everyone thought nothing innovative could have come out from Large Language Models (LLMs) and decidedly focused on agentic…
Rhauani Fazul·Oct 28Thinking fast with JevSometimes the AI component in an application only needs to answer a small question: which route should handle this request, does this item…A response icon1A response icon1
