Decision Models: When AI Decides Instead of Writes
A series on decision models, a class of models that take a program's state plus questions with a pre-declared answer space and return typed decisions with probabilities instead of generating text. TypeSafe AI's JEV is the running example: from the concept to the mechanics, the ecosystem and a concrete application, always separating what the vendor has published from the blog's own analysis.
- Decision Models: A New Branch Beside Generative LLMs
Most places we wire an LLM into software only need a decision: which team gets this ticket, should this transaction be blocked, does a person need to look. Yet we still make the model write prose and parse it back. A decision model flips that: declare the answer space first, get back a typed decision with probabilities.
- How JEV Works: Choice, Score, Noul and RLCD
One JEV call takes roughly 70–500 ms. In that window, a request made of state, a model name and typed questions goes in, and a set of probabilities comes out. This post opens each layer of that loop: the schema, the three question types, runnable code, the parallel sampler, RLCD, calibration, how to set thresholds, and the line between what TypeSafe has published and what nobody knows yet.
- The JEV Ecosystem: Official SDKs, Community Projects and Open System One Models
A compact list of the tools and repositories in the JEV ecosystem, grouped into three layers by who is responsible: official (the typesafe-ai org), community (calling the real JEV through the SDK or HTTP), and open / self-hosted (open models behind a server that speaks the same protocol). One line per tool: name, link, description.
- Designing a Web Data Extraction Chrome Extension with JEV
A case study written as a design and test plan: JEV only picks from a list of candidates, while code reads the DOM, re-checks the result and exports the data.