AI Gateway now supports TypeSafe clients and an HTTP API for Jev
Jev is now callable through TypeSafe clients, HTTP, or Vercel AI SDK, returning typed probabilistic decisions that agents can consume without parsing prose.
Vercel AI Gateway now exposes Jev through **three integration paths**: an existing TypeSafe client, a language-agnostic HTTP API, and AI SDK. Jev returns typed boolean, choice, or score answers with probabilities rather than generated text.
Use it where an agent needs a machine-readable decision boundary, such as continuation checks, model selection, evaluations, or tool approval. Existing TypeSafe users can migrate by changing the base URL and API key.
Vercel AI Gateway now exposes Jev through **three integration paths**: an existing TypeSafe client, a language-agnostic HTTP API, and AI SDK. Jev returns typed boolean, choice, or score answers with probabilities rather than generated text. Use it where an agent needs a machine-readable decision boundary, such as continuation checks, model selection, evaluations, or tool approval. Existing TypeSafe users can migrate by changing the base URL and API key. Jev is probabilistic, so a threshold such as **0.8** remains an application policy rather than certainty. The material supplies no calibration, quality, latency, or pricing results.
This broadens Jev from a gateway-listed evaluator into a more accessible control primitive across typed clients, raw HTTP, and AI SDK. It confirms that probabilistic, machine-readable judgments can sit inside routing and approval flows, but also sharpens the boundary: application-defined thresholds and external safeguards remain necessary because no calibration or operational results are supplied.