prodloop-observability-sdk 0.1.0

Python SDK for evaluating AI voice bot calls via Prodloop APIs.

Prodloop Observability SDK

Python SDK to evaluate AI voice bot calls through the Prodloop evaluation service.

Install

pip install prodloop-observability-sdk

Quickstart

from prodloop import ProdloopClient, EvaluationParameter

client = ProdloopClient(api_key="sk_live_...")

result = client.evaluate_call(
    audio_file_path="call.mp3",
    parameters=[
        EvaluationParameter.E2E_RESPONSE_TIME,
        EvaluationParameter.HALLUCINATION,
    ],
    thresholds={"e2e_response_time_max_ms": 800},
)

print(result)

Extraction Validation

To validate extraction quality, pass both extraction_schema and bot_captured_variables:

result = client.evaluate_call(
    audio_file_path="call.mp3",
    parameters=[EvaluationParameter.EXTRACTION_VARIABLES],
    extraction_schema={"customer_name": "string"},
    bot_captured_variables={"customer_name": "ram"},
)

Response includes:

• extraction_variables
• extraction_validation

Supported Parameters

• e2e_response_time
• turn_by_turn_latency
• hallucination
• extraction_variables
• interruption_behavior

Authentication

Pass your Prodloop API key in the SDK constructor.
The SDK sends it as a Bearer token in the Authorization header.

Errors

• ValidationError: invalid local inputs (file path, parameters, etc.)
• APIError: backend/API-level failures (status_code, message)

Local Demo

Use the included demo script:

export PRODLOOP_API_KEY="sk_live_..."
python demo/use_sdk.py --audio-file "/absolute/path/to/call.mp3"

Documentation Site

This repo includes MkDocs docs under docs/.

pip install -e ".[docs]"
mkdocs serve