Sign in
← AI PulseSep 16, 2026

Wire · news · Multi-source brief

Vercel AI SDK Adds TypeSafe Provider for Evaluation, Enhances Tool Discovery

The Vercel AI SDK has introduced a TypeSafe provider for experimental_evaluate, enabling native Choice, Score, and Boolean questions, structured JSON rubrics, and workflow serialization.

By Illumora Editorial

Source · Sep 16, 2026, 6:26 PM · On Illumora · Sep 16, 2026, 6:38 PM

Media from the primary source — shown here so you can stay on Illumora.

Synthesized from multiple allowlisted primaries on the same event. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →Vercel AI SDK Changelog — Release @ai-sdk/huggingface@2.0.50 · vercel/ai
Save

The Vercel AI SDK has released updates across several packages, including @ai-sdk/huggingface@2.0.50, @ai-sdk/hume@3.0.42, and @ai-sdk/klingai@4.0.44. A significant addition is the TypeSafe provider for experimental_evaluate, which supports various evaluation capabilities.

Key Points

  • The TypeSafe provider for experimental_evaluate has been added to the Vercel AI SDK.
  • This provider supports native Choice, Score, and Boolean questions within a single request.
  • It also enables structured JSON rubrics, probability distributions, confidence metadata, and workflow serialization.
  • The ai package, version 7.0.103, now includes mid-conversation tool discovery and updates for code-mode.
  • Default Node.js downloads are protected by DNS validation and connection pinning, even when frameworks or instrumentation wrap global fetch.
  • The rawInput in output-error UI message parts has been deprecated.

Context

According to the Vercel AI SDK changelog, these updates are part of ongoing development to enhance the SDK's capabilities. The introduction of the TypeSafe provider aims to offer more robust and structured evaluation methods for AI models. The changelog also indicates improvements in tool discovery within conversations and strengthened security measures for Node.js downloads.

Why It Matters

These updates provide developers with more advanced tools for evaluating AI model outputs and integrating AI functionalities into their applications. The structured evaluation capabilities can lead to more precise and reliable assessments of model performance, while improved tool discovery can streamline conversational AI experiences.

What To Do

  • Review the documentation for the new TypeSafe provider and experimental_evaluate function.
  • Explore the updated ai package (7.0.103) for mid-conversation tool discovery features.
  • Note the deprecation of rawInput in output-error UI message parts and adjust existing code if necessary.
  • Verify that Node.js downloads within your projects benefit from the enhanced DNS validation and connection pinning.