import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';

Getting started

This guide will walk you through creating a working eval that tests prompts across multiple models and opens a web view for comparing outputs.

After installing promptfoo, you can set up your first config file in a few ways:

Running an example

Set up your first config file with a pre-built example by running this command with npx, npm, or brew:

This will create a new directory with a basic example that tests translation prompts across different models. The example includes:

• A configuration file promptfooconfig.yaml with sample prompts, providers, and test cases.
• A README.md file explaining how the example works.

Most providers need authentication. For OpenAI:

export OPENAI_API_KEY=sk-abc123

Then navigate to the example directory, run the eval, and view results:

Set up via the CLI

To start from scratch, run promptfoo init to create a config through an interactive CLI walkthrough:

Set up via the Web UI

If you prefer a visual interface, run promptfoo eval setup to configure your first eval through the web UI:

This opens a browser-based setup flow that walks you through creating prompts, choosing providers, and adding test cases.

Configuration

Now that you've created an initial configuration, you can update promptfooconfig.yaml with your own prompts, providers, and test cases:

1. Set up your prompts: Open promptfooconfig.yaml and add prompts that you want to test. Use double curly braces for variable placeholders: {{variable_name}}. For example:

   yamlCopy

   prompts:
     - 'Convert the following English text to {{language}}: {{input}}'
   

   » More information on setting up prompts

2. Add providers: Add providers to specify AI models you want to test. Promptfoo supports 60+ providers including OpenAI, Anthropic, Google, and many others:

   yamlCopy

   providers:
     - openai:chat:gpt-5.4
     - openai:chat:gpt-5.4-mini
     - anthropic:messages:claude-opus-4-6
     - google:gemini-3-pro-preview
     # Or use your own custom provider
     - file://path/to/custom/provider.py
   

   This includes cloud APIs, local models like Ollama, and custom Python or JavaScript code.

   » See all providers

3. Add test inputs: Add some example inputs for your prompts. Optionally, add assertions to set output requirements that are checked automatically.

   For example:

   yamlCopy

   tests:
     - vars:
         language: French
         input: Hello world
       assert:
         - type: contains
           value: 'Bonjour le monde'
     - vars:
         language: Spanish
         input: Where is the library?
       assert:
         - type: icontains
           value: 'Dónde está la biblioteca'
   

   When writing test cases, think of core use cases and potential failures that you want to make sure your prompts handle correctly.

   » More information on setting up tests

4. Run the evaluation: Make sure you're in the directory containing promptfooconfig.yaml, then run:

   <Tabs groupId="promptfoo-command"> <TabItem value="npx" label="npx" default> ```bash npx promptfoo@latest eval ``` </TabItem> <TabItem value="npm" label="npm"> ```bash promptfoo eval ``` </TabItem> <TabItem value="brew" label="brew"> ```bash promptfoo eval ``` </TabItem> </Tabs>

   This tests every prompt, model, and test case.

5. Review outputs: After the evaluation is complete, open the web viewer to review the outputs:

   <Tabs groupId="promptfoo-command"> <TabItem value="npx" label="npx" default> ```bash npx promptfoo@latest view ``` </TabItem> <TabItem value="npm" label="npm"> ```bash promptfoo view ``` </TabItem> <TabItem value="brew" label="brew"> ```bash promptfoo view ``` </TabItem> </Tabs>

Asserts

The YAML configuration format runs each prompt through a series of test cases and checks if they meet the specified asserts.

Asserts are optional. Many people get value out of reviewing outputs manually, and the web UI helps facilitate this.

:::tip See the Configuration docs for a detailed guide. :::

Examples

The examples below cover a few common eval patterns: prompt quality, model quality, RAG quality, and agent quality.

Prompt quality

In this example, we evaluate whether adding adjectives to the personality of an assistant bot affects the responses.

You can quickly set up this example by running:

# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: Automatic response evaluation using LLM rubric scoring

# Load prompts
prompts:
  - file://prompts.txt
providers:
  - openai:chat:gpt-5.4
defaultTest:
  assert:
    - type: llm-rubric
      value: Do not mention that you are an AI or chat assistant
    - type: javascript
      # Shorter is better
      value: Math.max(0, Math.min(1, 1 - (output.length - 100) / 900));
tests:
  - vars:
      name: Bob
      question: Can you help me find a specific product on your website?
  - vars:
      name: Jane
      question: Do you have any promotions or discounts currently available?
  - vars:
      name: Ben
      question: Can you check the availability of a product at a specific store location?
  - vars:
      name: Dave
      question: What are your shipping and return policies?
  - vars:
      name: Jim
      question: Can you provide more information about the product specifications or features?
  - vars:
      name: Alice
      question: Can you recommend products that are similar to what I've been looking at?
  - vars:
      name: Sophie
      question: Do you have any recommendations for products that are currently popular or trending?
  - vars:
      name: Jessie
      question: How can I track my order after it has been shipped?
  - vars:
      name: Kim
      question: What payment methods do you accept?
  - vars:
      name: Emily
      question: Can you help me with a problem I'm having with my account or order?

From the newly created directory, run npx promptfoo@latest eval to execute this example:

This command will evaluate the prompts, substituting variable values, and output the results in your terminal.

You can also output a spreadsheet, JSON, YAML or HTML.

Model quality

In this next example, we evaluate the difference between GPT-5.4 and GPT-5.4 Mini outputs for a given prompt:

You can quickly set up this example by running:

# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: Comparing OpenAI flagship and mini models performance on riddles

prompts:
  - 'Solve this riddle: {{riddle}}'

providers:
  - openai:chat:gpt-5.4
  - openai:chat:gpt-5.4-mini

defaultTest:
  assert:
    # Inference should always cost less than this (USD)
    - type: cost
      threshold: 0.002
    # Inference should always be faster than this (milliseconds)
    - type: latency
      threshold: 3000

tests:
  - vars:
      riddle: 'I speak without a mouth and hear without ears. I have no body, but I come alive with wind. What am I?'
    assert:
      # Make sure the LLM output contains this word
      - type: contains
        value: echo
      # Use model-graded assertions to enforce free-form instructions
      - type: llm-rubric
        value: Do not apologize
  - vars:
      riddle: "You see a boat filled with people. It has not sunk, but when you look again you don't see a single person on the boat. Why?"
    assert:
      - type: llm-rubric
        value: explains that there are no single people (they are all married)
  - vars:
      riddle: 'The more of this there is, the less you see. What is it?'
    assert:
      - type: contains
        value: darkness
  - vars:
      riddle: >-
        I have keys but no locks. I have space but no room. You can enter, but
        can't go outside. What am I?
  - vars:
      riddle: >-
        I am not alive, but I grow; I don't have lungs, but I need air; I don't
        have a mouth, but water kills me. What am I?
  - vars:
      riddle: What can travel around the world while staying in a corner?
  - vars:
      riddle: Forward I am heavy, but backward I am not. What am I?
  - vars:
      riddle: >-
        The person who makes it, sells it. The person who buys it, never uses
        it. The person who uses it, doesn't know they're using it. What is it?
  - vars:
      riddle: I can be cracked, made, told, and played. What am I?
  - vars:
      riddle: What has keys but can't open locks?
  - vars:
      riddle: >-
        I'm light as a feather, yet the strongest person can't hold me for much
        more than a minute. What am I?
  - vars:
      riddle: >-
        I can fly without wings, I can cry without eyes. Whenever I go, darkness
        follows me. What am I?
  - vars:
      riddle: >-
        I am taken from a mine, and shut up in a wooden case, from which I am
        never released, and yet I am used by almost every person. What am I?
  - vars:
      riddle: >-
        David's father has three sons: Snap, Crackle, and _____? What is the
        name of the third son?
  - vars:
      riddle: >-
        I am light as a feather, but even the world's strongest man couldn't
        hold me for much longer than a minute. What am I?

Navigate to the newly created directory and run npx promptfoo@latest eval or promptfoo eval. Also note that you can override parameters directly from the command line.

For example, if you run this command:

It produces the following table, with Gemini models replacing the GPT models in the config:

A similar approach can be used to run other model comparisons. For example, you can:

• Compare GPT-5.4 reasoning effort settings (see GPT reasoning effort comparison)
• Compare models with different temperatures (see GPT temperature comparison)
• Compare open-source models (see Comparing Open-Source Models)
• Compare Retrieval-Augmented Generation (RAG) with LangChain vs. regular GPT (see LangChain example)

RAG quality

In this example, we evaluate whether RAG outputs are factual, relevant, and grounded in the retrieved context.

You can quickly set up this example by running:

From the newly created directory, run npx promptfoo@latest eval or promptfoo eval to grade outputs on factuality, answer relevance, context recall, context relevance, and context faithfulness. For a deeper walkthrough, see the RAG evaluation guide.

Agent quality

In this example, we evaluate an OpenAI Agents SDK workflow that uses tools for dice rolls, inventory checks, scene descriptions, and character stats.

You can quickly set up this example by running:

From the newly created directory, run npm install, then npx promptfoo@latest eval or promptfoo eval to test tool use and response quality across multi-turn scenarios. For task completion and trajectory checks, see the agent evaluation guide and tracing docs.

Next steps

Now that you've run your first eval, here are some ways to go deeper:

Customize your setup:

• Configuration guide - Detailed walkthrough of all config options
• Providers documentation - All 60+ supported AI models and services
• Assertions & Metrics - Automatically grade outputs on a pass/fail basis

Explore use cases:

• Agent evaluation - Test whether agents complete tasks and follow expected trajectories
• RAG evaluation - Test retrieval-augmented generation pipelines
• Red teaming quickstart - Scan your LLM app for security vulnerabilities
• CI/CD integration - Run evals automatically on every PR

Learn from examples:

• More examples in our GitHub repository