{
  "schema_version": "1.1",
  "id": "s4:https://vercel.com/changelog/ai-gateway-now-supports-typesafe-clients-and-http-api-for-jev",
  "slug": "ai-gateway-now-supports-typesafe-clients-and-http-api-for-jev-18y9alu",
  "url": "https://feed7.dev/p/ai-gateway-now-supports-typesafe-clients-and-http-api-for-jev-18y9alu",
  "title": "AI Gateway now supports TypeSafe clients and an HTTP API for Jev",
  "why_included": "Jev is now callable through TypeSafe clients, HTTP, or Vercel AI SDK, returning typed probabilistic decisions that agents can consume without parsing prose.",
  "summary": "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.",
  "practical_implication": "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.",
  "agent_context": "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.\n\nUse 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.\n\nJev 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.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/ai-gateway-now-supports-typesafe-clients-and-http-api-for-jev",
    "published_at": "2026-09-21T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "benchmark",
  "domains": [
    "coding"
  ],
  "topics": [
    "agent-evals",
    "agent-reliability",
    "gateways"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "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."
  ],
  "connected_context": {
    "meaning": "Jev adds a narrow, typed decision primitive alongside the gateway’s existing routing, transport, and evaluation infrastructure. It can simplify machine-enforced branches and acceptance checks, but its probabilities still require application thresholds and measured calibration; it does not replace access controls, trajectory-level evaluation, or deterministic production checks.",
    "corpus_size": 843,
    "generated_at": "2026-09-22T09:07:57.917Z",
    "connections": [
      {
        "title": "How Tailscale built a customer-facing model router on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/blog/how-tailscale-built-a-customer-facing-model-router-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/how-tailscale-built-a-customer-facing-model-router-on-ai-gateway-186s3tu",
        "reason": "Jev could supply structured routing decisions within this gateway pattern, while Tailscale’s identity checks and credential isolation remain separate enforcement controls."
      },
      {
        "title": "Run Terminal-Bench and other Harbor evals on Vercel Sandbox",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/run-terminal-bench-and-other-harbor-evals-on-vercel-sandbox",
        "feed7_url": "https://feed7.dev/p/run-terminal-bench-and-other-harbor-evals-on-vercel-sandbox-0o8aa4r",
        "reason": "Harbor’s isolated evaluation loop provides a way to test Jev thresholds and decision quality before using its probabilistic outputs in agent control flow."
      },
      {
        "title": "Mousepower: agents that can’t be measured, can’t be managed. — Maximillian Piras, Yutori",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=8KkibGU_DDY",
        "feed7_url": "https://feed7.dev/p/mousepower-agents-that-can-t-be-measured-can-t-be-managed-maximillian-pi-0q5vhzc",
        "reason": "Jev’s booleans, choices, and scores can implement the cheap acceptance checks advocated by Mousepower, provided teams first define trustworthy outcome criteria."
      },
      {
        "title": "The Future of Evals: From LLM as a Judge to Agent as a Judge — Aparna Dhinakaran, Arize AI",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=q2JrUKBMf0w",
        "feed7_url": "https://feed7.dev/p/the-future-of-evals-from-llm-as-a-judge-to-agent-as-a-judge-aparna-dhina-1fu560o",
        "reason": "Jev narrows evaluation to predefined typed questions, whereas agent-based judging addresses failures across variable trajectories; the approaches cover different evaluation scopes."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-21T00:00:00.000Z",
  "modified_at": "2026-09-21T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/ai-gateway-now-supports-typesafe-clients-and-http-api-for-jev-18y9alu",
    "json": "https://feed7.dev/p/ai-gateway-now-supports-typesafe-clients-and-http-api-for-jev-18y9alu.json",
    "markdown": "https://feed7.dev/p/ai-gateway-now-supports-typesafe-clients-and-http-api-for-jev-18y9alu.md"
  }
}