A scaled-down document Q&A demo showing the retrieval-augmented generation pattern used in Offerio AI: ingest a small sanitized document set, ask a question, see the retrieved context and generated answer.
$ query
What deployment targets does Offerio AI support?
$ retrieved context
[doc: infra-notes.md] Offerio AI ships as a Next.js app deployed to Vercel, with background jobs and vector store access handled separately.
$ response
Offerio AI deploys to Vercel, with the RAG pipeline and vector store running as separate background services.
This is a static, illustrative sample — not connected to any production or client system.