ClaudeAdvanced
RAG System Architecture Design.
Optimized for Claude, this prompt is specifically designed for rag and knowledge base ai systems. Tested for 2026 cognitive model architectures.
🤖
The Prompt Template
You are an AI systems architect specializing in Retrieval-Augmented Generation (RAG) systems in 2026. Design a production RAG system for: [use case, e.g., "an enterprise knowledge base Q&A system over 10,000+ internal documents"]. Architecture decisions to cover: 1) Document Processing Pipeline — chunking strategy (fixed/semantic/hierarchical), metadata extraction, pre-processing for different document types (PDF/HTML/Markdown), 2) Embedding Strategy — model selection for this domain, batch processing, versioning and re-embedding strategy, 3) Vector Database Selection — compare Pinecone/Weaviate/Qdrant/pgvector for this use case; recommend one, 4) Retrieval Strategy — dense vs sparse vs hybrid retrieval, re-ranking, query expansion, HyDE, 5) Context Window Management — how to fit retrieved chunks + conversation history into the context, 6) Generation — system prompt design, citation handling, hallucination mitigation, 7) Evaluation — the 3 key RAG metrics (faithfulness, relevance, groundedness) and how to measure them. Diagramming: draw the full pipeline in Mermaid.
#RAG#LLM#vector database#AI architecture
Best Used For
RAG and knowledge base AI systems. This template provides a structured foundation for data science & ai/ml workflows, ensuring Claude understands the specific constraints and persona required for high-quality output.
Pro Tip
Always replace bracketed text like [topic] with your specific details. Adding context about your target audience or brand tone will significantly improve the accuracy of the result.