What problem does it solve? LLM training data often contains outdated or incorrect information about the Vercel platform, leading to wrong recommendations such as defaulting to Edge runtime, assuming streaming requires Edge, or referencing deprecated products like Vercel Postgres and Vercel KV. ## Core Features & Use Cases - Knowledge Corrections: Overrides stale assumptions about Edge Functions, Fluid Compute, streaming/SSE, Node.js versions, timeouts, pricing, and package size limits. - New Product Awareness: Introduces recent Vercel offerings such as eve, AI Gateway, Queues, Sandbox, Rolling Releases, BotID, and the MCP server. - vercel.ts Configuration: Documents the TypeScript-based project configuration format that replaces vercel.json. - Use Case: When a user asks how to stream AI responses on Vercel, the assistant correctly recommends the default Node.js Fluid Compute runtime instead of unnecessarily switching to the Edge runtime. ## Quick Start Ask the assistant how to configure streaming, runtimes, or project settings on Vercel and it will apply the corrected platform knowledge automatically.
