
Rsc Streaming Ui
Vercel AI SDK (`ai` npm package) · Vercel AI SDK
AI SDK — Vercel AI SDK
Evaluates Vercel AI SDK's RSC Streaming & UI Generation across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI SDK eval coverage.
About Vercel AI SDK
Vercel AI SDK is the open-source TypeScript-first AI framework from Vercel — the `ai` npm package. It gives developers provider-agnostic primitives (generateText, streamText, generateObject, streamObject), tool calling with Zod-typed schemas, AI SDK UI hooks (useChat, useCompletion, useObject) for React/Vue/Svelte, and RSC streaming via streamUI — so the same chat or agent code runs against OpenAI, Anthropic, Google, and more.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Operator's RSC streamUI tool `getWeather.generate` returns a plain object `{ temp: 72 }`. The page never renders the weather card. | In streamUI, each tool's `generate` (async generator or function) must yield and/or return a React node, not raw data. Wrap data in a server component (`<WeatherCard data={...} />`). The streamed result is then a React tree the client can render via useUIState. | Pass / FailAi Platformhigh |
| 02 | Operator uses createAI({ actions: { submitMessage } }) and also exposes submitMessage as a `use server` action elsewhere, leading to duplicate request handlers. | Actions registered in createAI become available via useActions() on the client and execute on the server in the AI context. Choose one registration site — duplicating leads to inconsistent AIState updates and double-billed model calls. | Pass / FailAi Platformhigh |
| 03 | Operator mutates `aiState.get()` directly via array.push to add a message; useUIState consumers don't re-render. | Treat AIState as immutable. Call `aiState.update(prev => [...prev, msg])` (or `.done(...)` at the end of the action) so consumers re-render. Pair AIState (server-persisted message log) with UIState (client-rendered tree) — do not collapse them into a single store. | Pass / FailAi Platformhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Vercel Ai Sdk
- Ai Platform
- Rsc Streaming Ui
Recommended for
Works with
Related evals
Browserbase
Evaluates Browserbase's Captcha Handling across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
View Code AssistantBrowserbase
Evaluates Browserbase's Concurrency & Rate Limits across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
View Code AssistantBrowserbase
Evaluates Browserbase's Live Debugging & Session Inspector across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
ViewFrequently asked questions
What does the Rsc Streaming Ui eval for Vercel AI SDK Vercel AI SDK (`ai` npm package) test?+
Evaluates Vercel AI SDK's RSC Streaming & UI Generation across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI SDK eval coverage.
How is the Rsc Streaming Ui eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Rsc Streaming Ui pack for Vercel AI SDK Vercel AI SDK (`ai` npm package) contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Rsc Streaming Ui pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.