Building with Jev
An Independent Developer's Guide to Typed AI Decisions, Scoring and Routing in Production Software
-
- $0.99
-
- $0.99
Publisher Description
A practical, independent guide to building software that makes typed AI decisions with Jev, the decision model from TypeSafe AI that returns choices, scores and yes-probabilities with confidence instead of generated text. The book explains what a decision model is, when it is a better fit than rules, a classical classifier or a general-purpose language model, and when it is not. You learn the core ideas of state, typed questions and answers; how to handle API keys safely and call the service from Python, TypeScript and plain HTTP. Later chapters show how to design state, write clear Choice, Score and Noul questions, and turn probabilities and confidence into thresholds based on the real cost of errors. Pattern chapters cover routing and triage, moderation-style classification, lead scoring and ranking, and using decisions to select tools and guard inputs and outputs around language models and agents. The final part covers evaluation and monitoring, privacy and fairness in automated decisions under GDPR, the EU AI Act, India's DPDP Act, Brazil's LGPD and the CCPA, cost and latency budgeting, fallbacks, and an abstraction layer that limits vendor lock-in. Includes checklists, a hands-on lab, study questions with answers and a glossary.
This book is an independent publication and is not authorized, sponsored or endorsed by any company whose products it mentions. All trademarks belong to their respective owners and are used only for identification. This book was drafted with generative AI tools and checked with automated tools. Tools, features and prices change often; confirm them in current documentation.