Multi-step prompt sequences for complex AI workflows.
181 tools found
Staged agent workflow that converts database change requests into validated SQL with impact analysis, rollout plans, and traceability artifacts.
Multi-step prompt workflow that builds a continuous improvement loop for OpenAI Agents SDK agents using traces, human and LLM feedback, Promptfoo evals, and
A cookbook demonstrating how to connect OpenAI's Agents SDK Computer Use tool to Daytona sandboxes, enabling agents to see and control a Linux desktop with
Multi-step prompt workflow that migrates legacy code by running an OpenAI agent outside sandboxed execution environments, validating each repo shard with tests
Three-phase agent workflow (review, repair, validate) that uses Codex CLI to detect and fix stale API documentation through iterative feedback loops.
A fast-validating Qdrant embedding search fixture with a minimal local article set, derived from the Cookbook Qdrant search example.
Multi-step workflow for discovering recurring behavior patterns across thousands of agentic system traces using lower-level eval labels and population-level
Jupyter notebook demonstrating semantic search with OpenAI embeddings, LangChain's Oracle vector store, and Oracle AI Database Vector Search for RAG workflows.
Multi-step OpenAI Agents SDK workflow example demonstrating TypeScript features for building conversational agents that handle context beyond single-turn
Evaluate prompts against multiple LLM providers via a single endpoint using OrcaRouter for adaptive routing and comprehensive testing.
Prompt workflow that benchmarks OpenAI gpt-5.4 against gpt-5.4-mini on riddles and reasoning tasks to compare model performance and cost trade-offs.
Build custom Python providers for promptfoo to integrate with OpenAI, streamlining prompt engineering and AI-driven code development.
