Promptfoo tutorial: email drafter evaluation config

promptfooconfig.yaml

description: "Email drafter evaluation"

prompts:
  - |
    Draft an email based on these bullet points.
    Match the specified tone throughout the email.

    Bullet points:
    {{bullet_points}}

    Tone: {{tone}}

providers:
  - id: openai:chat:gpt-5
    label: "GPT-5"
  - id: anthropic:messages:claude-sonnet-4-6
    label: "Claude Sonnet 4"

defaultTest:
  assert:
    - type: latency
      threshold: 30000

tests:
  - vars:
      bullet_points: |
        - Recap of the design review decisions
        - Next steps: finalize mockups by Thursday
        - Ask if anyone has questions
      tone: "casual"
    assert:
      - type: icontains
        value: "mockups"
      - type: not-contains
        value: "Dear"
      - type: llm-rubric
        value: "The email uses a casual tone with contractions and short sentences"
      - type: python
        value: "50 <= len(output.split()) <= 200"

  - vars:
      bullet_points: |
        - Q1 revenue exceeded targets by 12%
        - New enterprise client onboarded
        - Hiring plan for Q2 approved
      tone: "formal"
    assert:
      - type: icontains
        value: "Q1"
      - type: llm-rubric
        value: "The email maintains a formal, professional tone throughout"

  - vars:
      bullet_points: |
        - API migration deadline is Friday at 5pm
        - Three endpoints still need updating
        - Downtime window is Saturday 2-6am
      tone: "urgent"
    assert:
      - type: icontains
        value: "Friday"
      - type: llm-rubric
        value: "The email conveys urgency with direct language and clear action items"
      - type: python
        value: "50 <= len(output.split()) <= 200"