How Tuner Works
Tuner is a lightweight analytics platform. It works by receiving call data from your voice AI platform via webhooks or our API. This data is then processed, analyzed, and made available in your Tuner dashboard.Data Flow
Data Sent to Tuner
After the call ends, your platform sends the call data (transcript, metadata, etc.) to Tuner.
Data Processed
Tuner processes the data, runs evaluations, and checks for red flags.
Integration Methods
Tuner offers two primary integration methods:No-Code Integration
Best For: Supported platforms like Retell. (We are always adding more tools)
Time to Integrate: ~5 minutes
Time to Integrate: ~5 minutes
API Integration
Best For: Custom voice AI stacks. Time to Integrate: ~30 minutes
Key Technical Concepts
Before you dive in, it is helpful to understand a few of Tuner’s core technical concepts. These are covered in detail in the Key Concepts Overview, but here is a brief summary:| Concept | Description |
|---|---|
| Evaluations | The process of analyzing a call against a set of criteria to determine its quality. |
| Guardrails | Rules that define what “bad” looks like. When breached, they trigger red flags or alerts. |
| Metrics | Quantitative measurements for every call, like talk time, silence duration, and sentiment. |
| Red Flags | Tags triggered when a critical issue is detected, like a hallucination or broken flow. |
Next Steps
Now that you have a high-level understanding of how Tuner works, dive into our integration guides to connect your agent.Key Concepts Overview
An overview of the core concepts that power the Tuner platform.
Connecting to LiveKit
Two-line SDK integration for LiveKit Agents.
Connecting to Pipecat
SDK integration for Pipecat Flows.
Custom Integration
Integrate your custom voice AI stack with the Tuner API.