src/workflows/{workflow_name}/
├── workflow.ts
├── steps.ts
├── evaluators.ts          # Runtime evaluators (optional)
├── types.ts
└── tests/
    ├── datasets/
    │   ├── happy_path.yml
    │   └── edge_case.yml
    └── evals/
        ├── evaluators.ts  # Offline eval test evaluators
        ├── workflow.ts     # Eval workflow definition
        └── judge_topic@v1.prompt  # LLM judge prompts (optional)

// tests/evals/evaluators.ts
import { verify, Verdict } from '@outputai/evals';
import { z } from '@outputai/core';

verify(options, checkFn)

{
  input,    // typed workflow input
  output,   // typed workflow output
  context: {
    ground_truth: Record<string, unknown>  // from dataset YAML
  }
}

import { verify, Verdict } from '@outputai/evals';
import { z } from '@outputai/core';

export const evaluateSum = verify(
  {
    name: 'evaluate_sum',
    input: z.object({ values: z.array(z.number()) }),
    output: z.object({ result: z.number() })
  },
  ({ input, output }) =>
    Verdict.equals(output.result, input.values.reduce((a, b) => a + b, 0))
);

export const lengthCheck = verify(
  { name: 'length_check', input: blogInput, output: blogOutput },
  ({ output, context }) =>
    Verdict.gte(output.blog_post.length, Number(context.ground_truth.min_length ?? 100))
);

import { verify, judgeVerdict, judgeScore, judgeLabel } from '@outputai/evals';

// Returns pass/partial/fail verdict from an LLM
export const evaluateTopic = verify(
  { name: 'evaluate_topic', input: blogInput, output: blogOutput },
  async ({ input, output, context }) =>
    judgeVerdict({
      prompt: 'judge_topic@v1',
      variables: {
        blog_title: output.title,
        blog_post: output.blog_post,
        required_topic: String(context.ground_truth.required_topic ?? input.topic)
      }
    })
);

// Returns a numeric score from an LLM
export const evaluateQuality = verify(
  { name: 'evaluate_quality', input: blogInput, output: blogOutput },
  async ({ input, output }) =>
    judgeScore({
      prompt: 'judge_quality@v1',
      variables: { blog_title: output.title, blog_post: output.blog_post, topic: input.topic }
    })
);

// Returns a string label from an LLM
export const evaluateTone = verify(
  { name: 'evaluate_tone', input: blogInput, output: blogOutput },
  async ({ output }) =>
    judgeLabel({
      prompt: 'judge_tone@v1',
      variables: { blog_title: output.title, blog_post: output.blog_post }
    })
);

# tests/evals/judge_topic@v1.prompt
---
provider: anthropic
model: claude-haiku-4-5-20251001
temperature: 0
maxTokens: 1000
---

<system>
You are an evaluation judge. Assess whether a blog post is faithfully about the required topic.

Return a JSON object with:
- verdict: "pass" if the blog clearly focuses on the topic, "partial" if it mentions the topic but lacks depth, "fail" if it is not about the topic
- reasoning: a brief explanation of your judgment
</system>

<user>
Required topic: {{ required_topic }}

Blog title: {{ blog_title }}

Blog post:
{{ blog_post }}

Judge whether this blog post is faithfully about the required topic.
</user>

// tests/evals/workflow.ts
import { evalWorkflow } from '@outputai/evals';
import { evaluateSum } from './evaluators.js';

export default evalWorkflow({
  name: 'simple_eval',
  evals: [
    {
      evaluator: evaluateSum,
      criticality: 'required',
      interpret: { type: 'boolean' }
    }
  ]
});

export default evalWorkflow({
  name: 'blog_generator_eval',
  evals: [
    {
      evaluator: lengthOfOutput,
      criticality: 'required',
      interpret: { type: 'boolean' }
    },
    {
      evaluator: evaluateTopic,
      criticality: 'required',
      interpret: { type: 'verdict' }
    },
    {
      evaluator: evaluateQuality,
      criticality: 'required',
      interpret: { type: 'number', pass: 0.7, partial: 0.4 }
    },
    {
      evaluator: evaluateContent,
      criticality: 'informational',
      interpret: { type: 'boolean' }
    },
    {
      evaluator: evaluateTone,
      criticality: 'informational',
      interpret: { type: 'string', pass: ['professional', 'informative'], partial: ['casual'] }
    }
  ]
});

name: basic_input
input:
  values:
    - 1
    - 2
    - 3
    - 4
    - 5
last_output:
  output:
    result: 15
  executionTimeMs: 100
  date: '2026-02-13T00:00:00.000Z'

name: stripe_blog
input:
  topic: "Stripe the payment processor"
  requirements: "Include a link to https://stripe.com/en-gb/pricing"
last_output:
  output:
    title: "Stripe: The Modern Payment Processing Platform"
    blog_post: |
      Stripe has revolutionized online payment processing...
  executionTimeMs: 5000
  date: '2026-02-16T00:00:00.000Z'
ground_truth:
  notes: "Known good case"
  evals:
    length_of_output:
      min_length: 100
    evaluate_topic:
      required_topic: "Stripe the payment processor"
    evaluate_content:
      required_content: "https://stripe.com/en-gb/pricing"

# Generate dataset from inline JSON input
output workflow dataset generate my_workflow --input '{"key": "value"}' --name my_test

# Generate from a scenario file
output workflow dataset generate my_workflow basic

# Run evals with cached output (fast, no re-execution)
output workflow test my_workflow --cached

# Run evals fresh and save results
output workflow test my_workflow --save

# Run specific datasets only
output workflow test my_workflow --dataset happy_path,edge_case

# List all datasets
output workflow dataset list my_workflow

# 1. Start the dev server
npm run dev

# 2. Generate datasets from real workflow runs
output workflow dataset generate blog_generator --input '{"topic": "AI"}' --name ai_post

# 3. Edit the dataset YAML to add ground_truth values for your evaluators

# 4. Run evals with --save to cache output and eval results
output workflow test blog_generator --save

# 5. Iterate on evaluators, re-run with cached output (fast)
output workflow test blog_generator --cached

# 6. List all datasets
output workflow dataset list blog_generator