#navbar img {
  height: 36px; /* e.g., 50px */
}


// {
//   "group": "API Documentation",
//   "pages": [
//     {
//       "group": "Calls",
//       "pages": [
//         "documentation/api/calls/introduction",
//         "documentation/api/calls/get-calls",
//         "documentation/api/calls/reevaluate-calls",
//         "documentation/api/calls/delete-call"
//       ]
//     },
//     {
//       "group": "Agents",
//       "pages": [
//         "documentation/api/agents/create-agents",
//         "documentation/api/agents/list-agents",
//         "documentation/api/agents/update-agents",
//         "documentation/api/agents/delete-agents"
//       ]
//     },
//     {
//       "group": "Metrics",
//       "pages": [
//         "documentation/api/metrics/create-metrics",
//         "documentation/api/metrics/generate-metrics",
//         "documentation/api/metrics/create-bulk-metrics",
//         "documentation/api/metrics/list-metrics",
//         "documentation/api/metrics/get-metrics",
//         "documentation/api/metrics/update-metrics",
//         "documentation/api/metrics/update-critical-workflow-metric",
//         "documentation/api/metrics/delete-metrics",
//         "documentation/api/metrics/types-of-metrics"
//       ]
//     },
//     {
//       "group": "Evaluators",
//       "pages": [
//         "documentation/api/evaluators/create-evaluators",
//         "documentation/api/evaluators/generate-evaluators",
//         "documentation/api/evaluators/update-evaluators",
//         "documentation/api/evaluators/list-evaluators",
//         "documentation/api/evaluators/get-evaluator",
//         "documentation/api/evaluators/running-evaluators",
//         "documentation/api/evaluators/create-from-transcript"
//       ]
//     },
//     {
//       "group": "Results",
//       "pages": [
//         "documentation/api/results/list-results",
//         "documentation/api/results/get-results",
//         "documentation/api/results/rerun-results",
//         "documentation/api/results/reevaluate-metrics"
//       ]
//     },
//     {
//       "group": "Runs",
//       "pages": [
//         "documentation/api/runs/get-runs-bulk"
//       ]
//     },
//     {
//       "group": "Personalities",
//       "pages": [
//         "documentation/api/personalities/list-personalities"
//       ]
//     },
//     {
//       "group": "Predefined Metrics",
//       "pages": [
//         "documentation/api/predefined-metrics/list-predefined-metrics"
//       ]
//     },
//     {
//       "group": "Phone Numbers",
//       "pages": [
//         "documentation/api/phone-numbers/list-inbound-phone-numbers"
//       ]
//     },
//     {
//       "group": "LLM Websocket",
//       "pages": [
//         "documentation/api/evaluators/llm-websocket-server-example"
//       ]
//     }
//   ]
// },


External API view set for managing metrics.
This view set provides endpoints to create, retrieve, update, and delete
metrics associated with AI agents within a specific organization.

Creating Metrics in Bulk

* `binary_workflow_adherence` - Binary Workflow Adherence
* `binary_qualitative` - Binary Qualitative
* `continuous_qualitative` - Continuous Qualitative
* `numeric` - Numeric
* `enum` - Enum

* `always` - Always
* `automatic` - Automatic
* `custom` - Custom

Custom configuration parameters for specific metrics

Knowledge base files associated with this metric

The overall score for this metric across all test sets

The AI agent this metric is associated with

Whether audio evaluation is enabled for this metric

Detailed description of what the metric evaluates

Type of evaluation (e.g., boolean, enum, score)

* `binary_workflow_adherence` - Binary Workflow Adherence
* `binary_qualitative` - Binary Qualitative
* `continuous_qualitative` - Continuous Qualitative
* `numeric` - Numeric
* `enum` - Enum

The evaluation trigger used for this metric

* `always` - Always
* `automatic` - Automatic
* `custom` - Custom

The evaluation trigger prompt used for this metric

The evaluation prompt used for this metric

Type of metric (e.g., basic, custom_prompt, custom_code)

* `basic` - Basic
* `custom_prompt` - Custom Prompt
* `custom_code` - Custom Code

* `basic` - Basic
* `custom_prompt` - Custom Prompt
* `custom_code` - Custom Code

api key

Cekura

Testing for AI Voice Agents. Launch in minutes not weeks by ensuring your agents deliver a seamless experience in every conversational scenario

Introduction

Explore our video tutorials to master AI voice agent testing and integration with Cekura.

Video Tutorials

This page provides examples of metrics and scenarios that can be used to test agent interactions. Each example includes both basic and advanced implementations, along with relevant scenarios and expected outcomes. 

Prompting Examples

Transcript Format

Guide to setting up and using chat-based testing with LLM websocket servers

Chat Based Testing

Documentation

API Reference

Dashboard

Support

Overview

Agent Description Guide

Metrics are used to understand and evaluate the performance of your AI Voice Agent

Pre-Defined Metrics

Personalities in Cekura define how your AI agents behave, communicate, and interact with users. They encompass the agent's tone, knowledge base, response style, and voice characteristics, allowing you to create unique and purposeful AI experiences.

Creating Custom Personalities

Learn how to quickly create and test voice agents on Cekura without requiring any external API keys or integrations.

Custom Agent

This guide will walk you through the process of setting up and testing voice agents using Retell integration in Cekura. When creating a new agent, you can select Retell as your provider from the available options in the agent creation interface.

Retell Agents

This guide will walk you through the process of setting up and testing voice agents using VAPI integration in Cekura. When creating a new agent, you can select VAPI as your provider from the available options in the agent creation interface.

VAPI Agents

Learn how to use your own backend system for simulation testing with Cekura by integrating a custom transcript provider.

Custom Integration Provider

This guide walks you through the process of testing outbound calls using evaluators. You'll learn how to retrieve evaluators with phone numbers and execute outbound call tests.

Testing Outbound Calls

To begin using observability features, you will need a Cekura account. If you do not have access, please contact [tarush@cekura.ai](mailto:tarush@cekura.ai).

Custom Observability

Monitor and analyze your VAPI-based voice agents

VAPI Observability

Monitor and analyze your Retell-based voice agents

Retell Observability

Metric Lab is a tool that allows you to create and manage custom metrics for your AI agents.

Create a new call log entry.

This endpoint allows users to create a call log by providing necessary data in the request body.
Requires a valid API key in the headers.

Observing Calls

Manage external call logs.

This view provides endpoints to retrieve, delete, and list call logs for external users.
A call log represents a record of a communication event, including details such as the agent involved,
the call ID, and the outcome of the call. This information is crucial for monitoring and evaluating
the performance of agents and the quality of interactions.

Required only when call_logs is “all” OR is number of first N calls. Only either of agent_id or assistant_id is required

Getting a Call Log

Getting Call Logs

Reevaluating Calls

Deleting Call Logs

External API view set for managing AI agents.
This view set provides endpoints to create, retrieve, update, and delete
AI agents associated with a specific organization, authenticated via API key.

Getting Agents

Creating an Agent

Updating an Agent

Deleting an Agent

Getting an Agent

Getting Metrics

Creating a Metric

Generating Metrics

Getting a Metric

Updating a Metric

External API view set for managing critical metric scenarios.
This view set provides endpoints to update and manage critical metric
scenarios associated with a specific organization.

Get Critical Metric Scenarios

Updating a Critical Metric Scenario

Deleting a Metric

External API view set for managing scenarios.
This view set provides endpoints to list, create, and manage scenarios
associated with a specific organization, authenticated via API key.

Getting Evaluators

Creating an Evaluator

Getting an Evaluator

Deleting an Evaluator

Updating an Evaluator

Running Evaluators

Generate Evaluator

Creating an Evaluator from Transcript

Create a new cron job for scheduled Evaluators execution

Creating a cronjob for evaluators

External API view set for retrieving results.
This view set allows users to access results associated with their
organization, providing endpoints to list and retrieve detailed results.

Get Results

Get an Result

Reevaluate Metrics

Rerun Results

External API view set for managing runs.
This view set provides endpoints to retrieve and manage runs associated with a specific organization.

Getting Runs with IDs

Runs Improve Prompt

External API view set for retrieving personalities.
This view set allows users to access predefined personalities that are
not associated with any organization.

Get Personalities

External API view set for retrieving predefined metrics.
This view set allows users to access predefined metrics that are
not associated with any organization.

Get Predefined Metrics

External API view set for managing phone numbers.
This view set provides endpoints to list and manage phone numbers
associated with a specific organization.

Get Inbound Phone Numbers

Learn how to embed Cekura agent overview in your application using our embed widget. For token management details, see our [Token Generation](/embed/generate-token) and [Token Refresh](/embed/refreshing-expired-token) guides.

Overview Embedding

Learn how to embed Cekura agent calls in your application using our embed widget. For token management details, see our [Token Generation](/embed/generate-token) and [Token Refresh](/embed/refreshing-expired-token) guides.

Calls Embedding

Learn how to embed Cekura agent results in your application using our embed widget. For token management details, see our [Token Generation](/embed/generate-token) and [Token Refresh](/embed/refreshing-expired-token) guides.

API Reference

Creating Metrics in Bulk

Authorizations

Body

Response