Présentation du livre en françaisintelligence artificielle

JEV AND SYSTEM ONE AI

Name: JEV AND SYSTEM ONE AI
Author: Faramarz Kowsari

Building Fast, Calibrated, Decision-Native Software Beyond Generative LLMs

« JEV AND SYSTEM ONE AI » est un livre de Faramarz Kowsari dans le domaine intelligence artificielle. Cette page de découverte en français organise les métadonnées publiques du livre afin de rendre ses thèmes, son public, sa langue réelle de publication et ses accès officiels plus faciles à trouver.

Les métadonnées publiques rattachent ce titre à l'intelligence artificielle, aux outils d'IA modernes ou aux flux de travail fondés sur les prompts.

Langue de publication: anglais. Cette page est une orientation en français. Le livre lui-même est publié en anglais ; le titre, l'aperçu et les options d'achat sur Google Books correspondent à cette édition.

Voir sur Google Books Ouvrir l'aperçu gratuit Page originale du livre

De quoi parle ce livre ?

Les métadonnées publiques rattachent ce titre à l'intelligence artificielle, aux outils d'IA modernes ou aux flux de travail fondés sur les prompts.

Thèmes mis en avant

Decision-native AIJev and System One modelsTyped probabilistic decisionsState design for decision modelsSemantic yes/no probabilityClosed decision spaces and choice modelsOrdered scoring and bounded judgmentProbability versus confidenceCalibration and threshold designParallel intelligence and speculative fan-outLearned if-statementsConfidence-gated automationJev and LLM hybrid architecturesModel, tool and agent routing

Description publique originale du livre

anglais

JEV AND SYSTEM ONE AI examines a different way to place machine intelligence inside production software: not as a conversational destination that must generate prose, but as a fast, typed, probabilistic decision component. Using Jev and TypeSafe AI's System One framing as a case study, the book asks what changes when software needs a route, score, probability, gate, category, or bounded judgment rather than an essay. Its central architectural idea is compositional: deterministic code handles what is exact, decision models handle bounded semantic ambiguity, generative models handle language and open-ended reasoning, and people remain responsible for novelty, accountability, and high-consequence judgment. The book develops this idea from first principles through state design, semantic yes/no decisions, closed choice spaces, ordered scoring, parallel fan-out, calibration, confidence-gated automation, learned if-statements, model/tool/agent routing, guardrails, verification, retrieval, customer-service workflows, production architecture, observability, security, privacy, adversarial state, cost, throughput, governance, and human review. It also distinguishes probability from confidence, explains why type safety removes invalid output shapes without eliminating semantic error, and treats calibration, thresholds, fallback policies, evaluation sets, and operational traces as core engineering artifacts rather than optional afterthoughts. The treatment is deliberately skeptical of hype. The manuscript separates company claims from independently established facts, explicitly notes that Jev's internal architecture and training corpus are undisclosed, and emphasizes that fast or schema-valid decisions can still be wrong, drift over time, or be inappropriate for reasoning-heavy…

À qui s'adresse le livre ?

Le public visé est fondé sur la description publique du livre. Pour les lecteurs francophones, il faut noter que l'édition disponible est publiée en anglais.

For software engineers, AI engineers, ML practitioners, technical founders, product architects, platform teams and engineering leaders who are building production AI systems and want lower-latency, more testable and more controllable alternatives to routing every decision through a generative LLM.

Objectifs d'apprentissage publiés