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 LLM training data often contains outdated or incorrect information about the Vercel platform, leading to wrong recommendations such as defaulting to Edge runtime, using deprecated products like Vercel Postgres, or missing new capabilities like Fluid Compute and vercel.ts configuration. ## Core Features & Use Cases - Knowledge Correction: Overrides stale assumptions about Edge Functions, streaming, timeouts, pricing, and runtimes with current Vercel platform facts. - New Product Awareness: Introduces recent offerings such as Vercel AI Gateway, Vercel Queues, Vercel Sandbox, Rolling Releases, BotID, and the eve agent framework. - Integration Guidance: Directs the agent to load the marketplace skill first whenever a build requires an external service like a database, payments, or CMS. - Use Case: When a user asks how to stream AI responses on Vercel, the agent correctly recommends the default Node.js Fluid Compute runtime instead of unnecessarily switching to the Edge runtime. ## Quick Start Ask the agent to configure or deploy a Vercel project and it will apply the corrected platform knowledge automatically.