Generative AI struggles with the reliability needed for business process automation. TypeSafe's Jev is succeeding by using a classifier model, which is optimized for making structured, predictable decisions. This "boring" approach is better suited for automating tasks in accounting or customer service where accuracy is paramount.

The AI model market is segmenting. New, cheaper models like JEV handle simple, high-volume 'System 1' tasks (e.g., classification, ranking) far more efficiently than general-purpose LLMs. This carves out a significant portion of the total addressable market from incumbents.

The new Jev model from TypeSafe is not an LLM competitor but a complementary tool. It outputs numbers and confidence scores for specialized tasks like classification, which can then feed into a conversational LLM for user interaction, creating a more efficient and accurate workflow.

Jev, a "judgment model," is for high-volume, low-stakes decisions like classification and rating. Unlike LLMs, it doesn't write or reason but provides fast, cheap "snap judgments," making it ideal for automating micro-decisions in workflows.

The emergence of specialized models like JEV signals a shift away from a "one model fits all" approach. Instead of forcing a single, expensive LLM to perform all tasks, companies will build complex architectures using a "model stack." This involves using fast judgment models for routing and then invoking generative models only when necessary.

Unlike standard LLMs that generate text, Jev is optimized for making choices from predefined options (e.g., yes/no, 1-10 scale, pick from a list). This makes it a "System 1" model, ideal for high-speed classification, routing, and filtering tasks that serve as smart "if" statements within larger applications.

The API outputs—`no`, `score`, and `choice`—are intentionally designed as new concepts rather than mapping directly to existing types like booleans or integers. A `no` is a continuous probability, not a binary true/false. This forces developers to think differently about integrating probabilistic AI logic into code.

Traditional software relies on binary if-then statements. New judgment models like JEV fundamentally upgrade this by allowing those `if` conditions to understand "messy human context." This enables automation of complex processes like fraud detection, support routing, and lead scoring that previously required human interpretation of nuanced situations.

Judgment models like JEV make traditional ML techniques like classification and regression more accessible. Companies that currently use expensive LLMs for these tasks can now use a simpler, API-driven approach that is better suited for the job, without needing to build and host complex custom models from scratch.