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

# Workflows

## Docs

- [Build multi-step AI apps with Vellum’s Worfklows](https://docs.vellum.ai/product/workflows/introduction.md): Discover how Vellum Workflows streamline LLM call chains with a low-code interface, easy testing, and versioned deployments.
- [Streamline AI App Development with Vellum's Workflows](https://docs.vellum.ai/product/workflows/experimentation.md): Discover how Vellum's Workflows simplifies building AI apps by managing complex LLM call chains and business logic easily.
- [Building a RAG Chatbot from Scratch](https://docs.vellum.ai/product/workflows/tutorials/building-a-rag-chatbot.md): Learn how to build a complete RAG chatbot in Vellum's Workflow Builder, starting with a basic chatbot and then adding document context to reduce hallucinations and provide more accurate responses.
- [Nodes Overview](https://docs.vellum.ai/product/workflows/nodes/overview.md): Overview of all Vellum Workflow Node types.
- [Agent Node](https://docs.vellum.ai/product/workflows/nodes/agent-node.md): Simplify tool calling in workflows with automatic schema handling and loop logic
- [Prompt Node](https://docs.vellum.ai/product/workflows/nodes/prompt-node.md): Invoke LLMs with your prompts, optionally using variables from other nodes.
- [Prompt Deployment Node](https://docs.vellum.ai/product/workflows/nodes/prompt-deployment-node.md): Execute deployed prompts in your workflows.
- [Templating Node](https://docs.vellum.ai/product/workflows/nodes/templating-node.md): Apply Jinja templating to perform lightweight data transformations.
- [Search Node](https://docs.vellum.ai/product/workflows/nodes/search-node.md): Search against a Document Index, great for RAG.
- [API Node](https://docs.vellum.ai/product/workflows/nodes/api-node.md): Make an HTTP request to an API endpoint.
- [Code Execution Node](https://docs.vellum.ai/product/workflows/nodes/code-execution-node.md): Run custom Python or Typescript code.
- [Subworkflow Node](https://docs.vellum.ai/product/workflows/nodes/subworkflow-node.md): Makes Workflows reusable and more maintainable as they get more complex.
- [Map Node](https://docs.vellum.ai/product/workflows/nodes/map-node.md): Iterate over an array, executing a sub-workflow for each item.
- [Guardrail Node](https://docs.vellum.ai/product/workflows/nodes/guardrail-node.md): Run an inline evaluation using a pre-defined Metric.
- [Conditional Node](https://docs.vellum.ai/product/workflows/nodes/conditional-node.md): Branch your workflow based on a condition, also useful for error handling.
- [Merge Node](https://docs.vellum.ai/product/workflows/nodes/merge-node.md): Wait for one or multiple branches to complete before continuing.
- [Final Output Node](https://docs.vellum.ai/product/workflows/nodes/final-output-node.md): Exposes values you can use in your application, you may have more than one!
- [Error Node](https://docs.vellum.ai/product/workflows/nodes/error-node.md): Stop workflow execution and raise an error.
- [Note Node](https://docs.vellum.ai/product/workflows/nodes/note-node.md): A simple node that displays text to help annotate your Workflow.
- [Node Adornments](https://docs.vellum.ai/product/workflows/nodes/node-adornments.md): Learn how to use Node Adornments to add error handling and retry logic to individual nodes in your workflows.
- [Easy Integration with Vellum's API for Workflows](https://docs.vellum.ai/product/workflows/api-integration.md): Learn how to integrate and monitor your Workflow with Vellum's API, making production deployment quick and easy.
- [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
- [Function Calling](https://docs.vellum.ai/product/workflows/function-calling-with-chat-models.md): Learn how to use function calling with Chat Models in Vellum Workflows
- [Long Running Workflows](https://docs.vellum.ai/product/workflows/advanced/long-running-workflows.md): Best practices for handling workflows that take extended time to complete, including asynchronous execution patterns and timeout management.
- [Batching Executions](https://docs.vellum.ai/product/workflows/advanced/batching-executions.md): Process large volumes of Workflow executions efficiently using async execution and automatic queuing.
- [Static IPs](https://docs.vellum.ai/product/workflows/advanced/static-ips.md)
- [Examples and Walkthroughs](https://docs.vellum.ai/product/workflows/examples/overview.md): See interactive Vellum architectures and watch video walkthroughs of them! Use these as a great starting point for your own applications.
- [Prompt Chaining](https://docs.vellum.ai/product/workflows/examples/prompt-chain.md): Build a basic Prompt Chain that connects multiple prompts to create a more powerful workflow.
- [RAG Chatbot](https://docs.vellum.ai/product/workflows/examples/basic-rag-chatbot.md): Build a powerful chatbot that leverages Retrieval Augmented Generation (RAG) to provide accurate, context-aware responses based on your documents and knowledge base.
- [RAG Chatbot with Cohere Rerank](https://docs.vellum.ai/product/workflows/examples/rag-chatbot-with-cohere-rerank.md): Learn how to build a RAG chatbot that uses Cohere's Reranker to improve the quality of its responses
- [Customer Support Bot](https://docs.vellum.ai/product/workflows/examples/customer-support-bot.md): Create an intelligent customer support system that handles routine inquiries automatically while seamlessly escalating complex cases to human agents, demonstrating effective human-AI collaboration.
- [Convert PDF to CSV](https://docs.vellum.ai/product/workflows/examples/pdf-to-csv.md): Learn how to convert PDF documents into CSV format for easier data manipulation.
- [Summarize Images of Websites](https://docs.vellum.ai/product/workflows/examples/summarize-images-of-websites.md): Learn how to process and analyze website screenshots using multi-modal LLMs to extract meaningful insights and generate concise summaries of visual web content.
- [Parallelized Function Calls](https://docs.vellum.ai/product/workflows/examples/parallel-function-calls.md): Learn how to optimize workflow performance by executing multiple functions concurrently, enabling efficient processing of batch operations and parallel API calls.
- [Lookup Conference Attendees with Perplexity](https://docs.vellum.ai/product/workflows/examples/conference-attendees-lookup.md): Learn how to look up conference attendees and sort them based on their involvement with AI/LLMs.
- [Multi-Agent Content Creation](https://docs.vellum.ai/product/workflows/examples/multi-agent-chatbot.md): Learn how to orchestrate multiple AI agents working together to research, create, and optimize content through collaborative workflows and specialized roles.
- [LLMs Debating Each Other](https://docs.vellum.ai/product/workflows/examples/chatbots-debate.md): Explore an innovative approach where multiple language models engage in structured debates, demonstrating complex reasoning, argument construction, and dynamic interaction between AI agents.
- [Slack Support Bot, Cites Sources using Multiple Indexes](https://docs.vellum.ai/product/workflows/examples/slack-support-bot.md): Learn how to build a Slack support bot that cites sources using multiple indexes.
- [Automating PR Reviews](https://docs.vellum.ai/product/workflows/examples/automating-pr-reviews.md): Learn how to build an automated code review system using Vellum Workflows to analyze pull requests, deliver insightful feedback, and uphold coding standards across your engineering team.