> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.vellum.ai/product/workflows/common-architectures/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vellum.ai/_mcp/server.

# Common Architectures

## Docs

- [Common LLM Architectures](https://docs.vellum.ai/product/workflows/common-architectures/overview.md): Discover popular architectural patterns for building LLM applications with Vellum Workflows
- [RAG System Architecture](https://docs.vellum.ai/product/workflows/common-architectures/rag-system.md): Build a Retrieval Augmented Generation system to enhance LLM responses with relevant data
- [Escalation to a Human](https://docs.vellum.ai/product/workflows/common-architectures/human-escalation.md): Automatically route sensitive or complex messages to human operators
- [Prompt Retry Logic](https://docs.vellum.ai/product/workflows/common-architectures/prompt-retry.md): Implement error handling with automatic retries for non-deterministic failures
- [PDF Content Summarization](https://docs.vellum.ai/product/workflows/common-architectures/pdf-summarization.md): Extract and summarize the contents of PDF documents
- [Fallback Models](https://docs.vellum.ai/product/workflows/common-architectures/fallback-models.md): Learn how to implement dynamic model selection with fallback logic to handle errors and optimize cost/performance