Skip to main content

​
Create an Agent

  1. Go to Agent Settings (If you are a new user, click Create an Agent from the left navigation bar to get started.)
  2. Add name, contact number, and language of the agent to be tested
  3. Add Agent Description.

​
Agent Description

Agent Description is a comprehensive overview of your voice conversational agent’s purpose, behaviour, and operational guidelines. It encapsulates all the instructions, prompts, and rules you provide to your AI agent.
By clearly articulating your agent’s description, you enable us to generate automatic, accurate evaluators.
Most customers include their agent’s main prompt here.
Description Pn

​
Type of Agent

For Single prompt agents, you can copy the agent’s main prompt here.
If you have multi-state agent, you can build a description in a json structure.
Note - We are very flexible with description so even if you copy paste all your prompts and paste as one huge prompt, we can process. JSON is the recommended approach.
[
{
"node_name": "<>",
"node_description": "<>"
},
{
"node_name": "<>",
"node_description": "<>"
}
]
If you have an agent with retell workflows, you can export the agent’s details as json from retell.
Go to agents > select the agent > click on export button (this will download a .json file) > copy the content of the file and paste it in agent description field.Retell Export
If you have an agent with vapi workflows, you can export the agent’s details as json from vapi.
Go to workflows > select the agent > click on code button on top right> copy the content shown and paste it in agent description field.Vapi Export
You can follow the same approach for other providers.

​
Agent End Point

Cekura supports multiple Agent Types to help you test different communication channels. Connect your Agent End Point to run simulations
  • Phone Number
  • WebRTC
Add Phone number in the Contact number section.Phonenumber(2) Pn
  • LLM Websocket
  • No Code Integration
LLM WebSocket enables real-time, two-way chat between your agent and the LLM, allowing dynamic and continuous conversation testing.Go to Chatbot Integration→ Choose Custom Chatbot→ Add WebSocket URLLLM Websocket Pn
Add Phone number in the Contact number sectionPhonenumber(2) Pn

​
Additional Settings (Optional)

Required to generate evaluators from the Knowledge BaseGo to Agent’s Knowledge→ Upload Knowledge base filesdownload.png
Required to test for tool calls in simulation. You can send us the transcript along with the tool calls.Go to Voice Integration→ Choose Provider as Custom→ Copy the Webhook URL→ Note your API key for authenticationCustomtoolcall Pn
No code integrations to automatically test for tool calls, pass production calls for observabilityIntegrations on Cekura connect your agents with providers like VAPI, Retell, ElevenLabs, LiveKit, Pipecat, or Custom setups — enabling seamless voice, chat, and real-time testing experiences.Go to Voice Integration→ Choose your desired Provider