Skip to content

Prodloop Observability SDK

Use the Prodloop SDK to programmatically evaluate AI voice bot calls from Python.

What you can do

  • send call recordings for evaluation
  • choose exactly which metrics to compute
  • pass thresholds and extraction schema
  • grade real calls against the bot prompt used in production
  • receive structured JSON responses
  • simulate prompt-only tester/bot conversations
  • run backend-owned self simulation or local user-orchestrated simulation

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)

Prompt Simulation

Prompt simulation lets you test a bot prompt without audio. Use plugins.LiteLLM to select any LiteLLM model route and choose one simulation parameter per request.

  • self_simulation: Prodloop backend runs the tester and bot with backend-owned provider credentials.
  • user_orchestrated: your local SDK process runs the bot with your credentials; Prodloop only receives bot replies and timing.

See Examples for full code.