Jump to content

Connect Leeroopedia MCP: Equip your AI agents to search best practices, build plans, verify code, diagnose failures, and look up hyperparameter defaults.

Principle:Promptfoo Promptfoo Interactive Project Setup

From Leeroopedia
Knowledge Sources
Domains Developer_Experience, Scaffolding
Last Updated 2026-02-14 08:00 GMT

Overview

An interactive scaffolding mechanism that generates a complete evaluation project through guided user selections of use case, language, and provider.

Description

Interactive Project Setup guides new users through creating a Promptfoo evaluation project from scratch. It uses interactive terminal prompts to collect preferences (use case type, programming language, LLM provider) and generates a fully configured project directory with config files, prompt templates, and example test data.

This solves the cold-start problem for new users by providing a working evaluation setup that can be immediately executed with `promptfoo eval`, while also educating users about available options.

Usage

Use this principle when initializing a new Promptfoo project. This is triggered by the `promptfoo init` CLI command and is the recommended entry point for first-time users.

Theoretical Basis

Pseudo-code Logic:

1. Prompt user: select use case (compare, rag, agent, redteam)
2. Prompt user: select programming language (if applicable)
3. Prompt user: select LLM provider(s) from supported list
4. Generate project files:
   a. promptfooconfig.yaml (from Nunjucks template)
   b. Prompt template files (.txt, .json, .py)
   c. Context/example files (for RAG use case)
5. Display success message with next steps

Related Pages

Implemented By

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment