Built on top of AI21’s advanced RAG Engine and enhanced with a planning layer, AI21 Maestro enables users to ask follow-up questions and receive grounded, context-aware answers.
You can extend AI21 Maestro capabilities using built-in tools that provide access to additional context and information from the web or your files.

File Search enables AI21 Maestro to retrieve information in a File Library through semantic search.
Web Search enables AI21 Maestro to include data from the web as context for the response generation.

​
Key Benefits

Chat with Your Data
Go beyond single-question answering by allowing follow-up questions, clarifications, and step-by-step problem-solving through a natural conversation.

Enterprise-Grade Accuracy
Built on retrieval-augmented generation (RAG), responses are grounded in your actual documents, not just model hallucination. It’s useful for internal tools and customer-facing applications alike.

Fully Managed & Easy to Deploy
Simply upload your documents (PDF, DOCX, TXT, HTML, or Markdown). The RAG Engine automatically indexes them, making setup fast and seamless. Data connectors are coming soon.

​
Deployment & Document Ingestion

  • Upload supported document types: .pdf, .docx, .txt, .md, .html.
  • Indexing is automatic.
  • The AI21 Maestro RAG system includes our in-house document parser, which provides high-quality parsing.
  • Data connectors to cloud sources.