Multi-step prompt sequences for complex AI workflows.
12 tools found
N8N Agent is a multi-step prompt workflow example demonstrating agent-based automation patterns for the n8n workflow platform, ready to run and test.
A complete RAG evaluation workflow that tests retrieval-augmented generation pipelines end-to-end using promptfoo's testing framework.
Gateway is a prompt workflow example demonstrating Cloudflare provider integration for promptfoo, enabling users to test and evaluate AI prompts through
A promptfoo workflow example demonstrating text-to-speech integration with ElevenLabs provider for testing and evaluating TTS prompt configurations.
Multi-step prompt workflow that builds a coding agent using GPT-5.1 and OpenAI Agents SDK to scaffold apps, apply patches, execute shell commands, and pull
Jupyter notebook demonstrating OpenAI Evals framework with custom datasets to compare gpt-4.1 and o4-mini models answering tiktoken repository questions via
Integrate OpenAI's Model Context Protocol (MCP) with promptfoo's Responses API to enhance AI model interaction and response management.
Example demonstrating MCP provider usage for evaluating MCP servers through direct tool calling evaluation.
LangGraph workflow routing RAG queries between web search and self-corrective retrieval using Mistral/Mixtral models via Ollama and Nomic embeddings.
Corrective RAG (CRAG) is a LangGraph workflow that self-grades retrieved documents for relevance and supplements poor results with web search to improve answer
Self-RAG enhances RAG with self-reflection and grading for retrieved documents and generations.
Self-RAG workflow using LangGraph that grades retrieved documents and generations for relevance, hallucination detection, and response quality, based on the
