Multi-step prompt sequences for complex AI workflows.
42 tools found
Promptfoo example for testing OpenAI's Realtime API: multi-turn voice/text conversations, function calling, and audio.
A promptfoo example collection covering OpenAI Responses API features - reasoning, MCP, caching, and more.
A promptfoo example for testing OpenAI tool-calling accuracy against the Chat Completions API.
A promptfoo example asserting on OpenTelemetry trace spans - counts, durations, and error rates for a RAG agent.
A Promptfoo example tracing a Python LLM provider's internals via OpenTelemetry, exporting spans in protobuf format for span-level eval assertions.
A promptfoo example dynamically constructing prompts by persona, task type, and context via a custom Vercel AI SDK provider.