> ## Documentation Index
> Fetch the complete documentation index at: https://docs.exulu.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Evaluations

> GraphQL types for testing and evaluating agent performance

## test\_cases

Test cases for evaluating agent performance.

```graphql theme={null}
type test_cases {
  id: ID!
  name: String!
  description: String
  inputs: JSON!                           # UIMessage[]
  expected_output: String!
  expected_tools: JSON                    # string[]
  expected_knowledge_sources: JSON        # string[]
  expected_agent_tools: JSON              # string[]
  createdAt: Date!
  updatedAt: Date!
  RBAC: RBACData
}
```

**Example:**

```graphql theme={null}
mutation {
  test_casesCreateOne(
    input: {
      name: "Weather Query"
      description: "User asks about weather"
      inputs: [
        { role: "user", content: "What's the weather like?" }
      ]
      expected_output: "Based on current data, it's 68°F and sunny."
      expected_tools: ["get_weather"]
    }
  ) {
    item {
      id
      name
    }
  }
}
```

## eval\_sets

Collections of test cases for batch evaluation.

```graphql theme={null}
type eval_sets {
  id: ID!
  name: String!
  description: String
  test_case_ids: JSON       # string[]
  createdAt: Date!
  updatedAt: Date!
  RBAC: RBACData
}
```

## eval\_runs

Evaluation execution records.

```graphql theme={null}
type eval_runs {
  id: ID!
  name: String!
  description: String
  agent_id: ID!
  test_case_ids: JSON           # string[]
  eval_functions: JSON          # string[]
  config: JSON
  scoring_method: String
  pass_threshold: Float
  timeout_in_seconds: Int
  createdAt: Date!
  updatedAt: Date!
  RBAC: RBACData
}
```

## Evaluation Workflow

1. Create **test\_cases** with expected inputs and outputs
2. Group test cases into **eval\_sets** for organized testing
3. Run **eval\_runs** to evaluate agent performance
4. Review results and iterate on agent improvements

## Related Types

<CardGroup cols={2}>
  <Card title="Agent Types" icon="robot" href="/api-reference/core-types/agent-types">
    Agents being evaluated
  </Card>

  <Card title="Job Types" icon="gears" href="/api-reference/core-types/job-types">
    Background eval execution
  </Card>

  <Card title="Back to Overview" icon="arrow-left" href="/api-reference/core-types/overview">
    View all core types
  </Card>
</CardGroup>