Multi-step prompt sequences for complex AI workflows.
42 tools found
A promptfoo workflow that evaluates GPT-4o model behavior across different temperature settings.
Promptfoo example covering every supported prompt format, with focus on dynamic-config prompt functions.
A promptfoo example generating test cases from JavaScript/TypeScript functions, both statically and dynamically.
Promptfoo example demonstrating how to configure different prompt sets for specific AI models.
A promptfoo example enforcing JSON-schema structured outputs across OpenAI, Azure OpenAI, and Anthropic.
A Promptfoo example showing how the test-level prompts field limits specific tests to specific prompts, instead of the default cartesian product.
Three patterns for overriding promptfoo's default assertion scoring function in config, JavaScript, or Python.
Promptfoo example workflow for evaluating Markdown rendering with language models.
Promptfoo max-score assertion for objective, weighted output selection - deterministic, no extra LLM calls.
A promptfoo example that demonstrates how to have an LLM grade its own output according to predefined expectations, with configuration via YAML or CSV test
The JavaScript OpenTelemetry tracing example for Promptfoo, tracing provider internals and validating tool-call trajectories.
Promptfoo example evaluating PydanticAI agents with structured-output validation and multiple assertion types.
