← Back to Skills
AI & Machine LearningTechnologyPlatinum

Designing complex RAG systems for enterprise applications.

RAG Architecture Designer

RAG pipelines, vector DBs, hybrid search

expertv5.0

Best for

  • Design enterprise RAG systems for customer support with 99.5% uptime requirements and <500ms latency
  • Architect hybrid search pipelines combining vector similarity with BM25 for legal document retrieval
  • Optimize RAG chunking strategies for technical documentation with complex nested structures
  • Build production RAG systems handling 10M+ documents with real-time updates and version control

What you'll get

  • Detailed architecture diagram with specific vector DB configuration (HNSW index parameters, sharding strategy), embedding model selection rationale, and chunking strategy with overlap percentages
  • Production deployment checklist with monitoring metrics, fallback strategies, and performance optimization recommendations for sub-500ms query response times
  • Technical implementation guide with code patterns for hybrid search, reranking algorithms, and hallucination detection mechanisms
Expects

Detailed requirements including data types, query patterns, scale expectations, latency constraints, and accuracy thresholds for the RAG system.

Returns

Complete RAG architecture blueprint with specific technology recommendations, configuration parameters, chunking strategies, and production deployment considerations.

What's inside

You are a Senior RAG Systems Architect. You design, deploy, and optimize production-grade Retrieval-Augmented Generation systems at scale. - Design RAG pipelines that balance retrieval precision, context utilization, and generation quality within strict latency and cost constraints rather than opti...

Covers

What You Do DifferentlyMethodologyWatch For
Not designed for ↓
  • ×Basic chatbot development without retrieval components
  • ×Simple vector database setup tutorials or basic embedding model comparisons
  • ×Training custom LLMs from scratch or fine-tuning foundation models
  • ×Frontend user interface design for RAG applications

SupaScore

90.13
Research Quality (15%)
9
Prompt Engineering (25%)
9.4
Practical Utility (15%)
8.6
Completeness (10%)
9.35
User Satisfaction (20%)
8.95
Decision Usefulness (15%)
8.65

Evidence Policy

Standard: no explicit evidence policy.

ragretrieval-augmented-generationvector-databaseembeddingschunkinghybrid-searchrerankingpineconepgvectorweaviatellminformation-retrievalhallucination-reduction

Research Foundation: 8 sources (1 academic, 5 official docs, 2 paper)

This skill was developed through independent research and synthesis. SupaSkills is not affiliated with or endorsed by any cited author or organisation.

Version History

v5.03/25/2026

v5.5 final distill

v2.02/26/2026

Pipeline v4: rebuilt with 3 helper skills

v1.0.02/14/2026

Initial release

Works well with

Need more depth?

Specialist skills that go deeper in areas this skill touches.

Common Workflows

Enterprise RAG Implementation

Complete RAG system design, database optimization, monitoring setup, and performance validation for enterprise deployment

rag-architecture-designerVector Database OptimizationLLM Observability Engineerapi-performance-testing-expert

© 2026 Kill The Dragon GmbH. This skill and its system prompt are protected by copyright. Unauthorised redistribution is prohibited. Terms of Service · Legal Notice