Skip to main content
The TypeScript SDK collects telemetry to help us improve evaluator quality, identify edge cases, and optimize performance.

​
What we collect

Telemetry is enabled by default and sends anonymous performance and metadata:
  • Performance metrics (latency, token usage)
  • Metadata (evaluator type, grade, SDK version)
Input text is not collected by default. You can opt in via recordInputs: true — see Enable input text collection below.
We never collect your API keys — only an anonymous identifier is used.

​
Example telemetry event

{
  "timestamp": "2026-02-05T19:30:00.000Z",
  "sdk_version": "0.1.0",
  "evaluator_type": "vocabulary",
  "grade": "3",
  "status": "success",
  "latency_ms": 3500,
  "text_length_chars": 456,
  "provider": "openai:gpt-4o-2024-11-20 + google:gemini-2.5-pro",
  "token_usage": {
    "input_tokens": 650,
    "output_tokens": 350
  },
  "metadata": {
    "stage_details": [
      {
        "stage": "background_knowledge",
        "provider": "openai:gpt-4o-2024-11-20",
        "latency_ms": 1200,
        "token_usage": {
          "input_tokens": 250,
          "output_tokens": 150
        }
      },
      {
        "stage": "complexity_evaluation",
        "provider": "google:gemini-2.5-pro",
        "latency_ms": 2300,
        "token_usage": {
          "input_tokens": 400,
          "output_tokens": 200
        }
      }
    ]
  }
}

​
Field reference

FieldDescription
timestampISO 8601 timestamp when evaluation started
sdk_versionVersion of the SDK (e.g., "0.1.0")
evaluator_typeWhich evaluator ran (e.g., "vocabulary", "sentence-structure")
gradeGrade level evaluated (e.g., "5", "K")
statusEvaluation outcome: "success" or "error"
error_codeError type if status is "error" (e.g., "Error", "TypeError")
latency_msTotal evaluation time in milliseconds
text_length_charsLength of input text in characters
providerLLM provider(s) used (e.g., "openai:gpt-4o", "google:gemini-2.5-pro")
token_usageTotal tokens consumed (input and output)
input_textThe text being evaluated — only included if recordInputs: true
metadata.stage_detailsPer-stage breakdown for multi-stage evaluators (optional)

​
Configuration

​
Default (anonymous)

Telemetry is on by default with no configuration required: 
const evaluator = new VocabularyEvaluator({
  googleApiKey: process.env.GOOGLE_API_KEY!,
  openaiApiKey: process.env.OPENAI_API_KEY!,
  // telemetry: true (default — anonymous)
});

​
Partner with us (authenticated)

Provide a partner key to help us support your specific use case and collaborate more directly: 
const evaluator = new VocabularyEvaluator({
  googleApiKey: process.env.GOOGLE_API_KEY!,
  openaiApiKey: process.env.OPENAI_API_KEY!,
  partnerKey: process.env.LEARNING_COMMONS_PARTNER_KEY!, // Contact us for a key
});
Reach out to get a partner key ↗

​
Disable telemetry completely

const evaluator = new VocabularyEvaluator({
  googleApiKey: process.env.GOOGLE_API_KEY!,
  openaiApiKey: process.env.OPENAI_API_KEY!,
  telemetry: false, // No data sent
});

​
Enable input text collection

const evaluator = new VocabularyEvaluator({
  googleApiKey: process.env.GOOGLE_API_KEY!,
  openaiApiKey: process.env.OPENAI_API_KEY!,
  telemetry: {
    enabled: true,
    recordInputs: true, // Also send input text with telemetry
  },
});