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

# Common LLM Architectures

> Discover popular architectural patterns for building LLM applications with Vellum Workflows

With Vellum Workflows' extensive Nodes and orchestration features, you can build a wide variety of LLM application architectures. Below you'll find common patterns that serve as excellent starting points for your own applications.

For more extensive example Workflows, [click here](/product/workflows/examples/overview) to view our examples section.

#### [RAG System](./rag-system)

Build a Retrieval Augmented Generation system to enhance LLM responses with relevant data.

#### [Escalation to a Human](./human-escalation)

Automatically route sensitive or complex messages to human operators.

#### [Prompt Retry Logic](./prompt-retry)

Implement error handling with automatic retries for non-deterministic failures.

#### [PDF Content Summarization](./pdf-summarization)

Extract and summarize the contents of PDF documents.

#### [Fallback Models](./fallback-models)

Implement dynamic model selection with fallback logic to handle errors and optimize cost/performance.