Skip to main content
An agent is a core building block of Calibrate. Agents can:
  • Process voice conversations using Speech To Text (STT) and Text To Speech (TTS)
  • Respond intelligently using LLM models following the instructions given to them
  • Use tools for structured data extraction

​
Quickstart

From the sidebar, click Agents to view your existing agents or create a new one.
Agents List

​
Create a new agent

Click the New agent button in the top right corner, fill the name of the agent and hit Create agent.
Create Agent
Once ready, you’ll be taken to the agent configuration page with multiple tabs.

​
Configure your agent

​
Add instructions and select providers

Configure the core agent behavior.
Agent tab
System prompt Define the context for the agent, its persona, how it should behave, and any guidelines it should follow. Write clear instructions.
Be specific about the agent’s tone, capabilities, and limitations in the system prompt.
For detailed guidance on writing effective system prompts, see ElevenLabs Prompting Guide and OpenAI Prompt Engineering Guide. Speech To Text Select the STT provider for the agent. Text To Speech Select the TTS provider for the agent. LLM Select the provider and model for the agent. Click Save in the top right to save your configuration.

​
Add tools

Add tools to enable structured outputs by the agent.
Tools tab
Click Add tool to attach tools to your agent. See the Tools guide for how to create tools. In-built tools The platform provides built-in tools like “End conversation” that are automatically available to all agents.

​
Define data extraction fields

Define fields for extracting structured data from conversations.
Data extraction tab
Click Add field to define custom data specifications to extract from conversation transcripts.

​
Add tests

Add tests to evaluate your agent’s performance.
Tests tab
  • Click Add test to attach tests to your agent
  • Click Run all tests to execute all tests for this agent
  • Click Compare models to benchmark different LLMs
See the LLM Testing guide for how to create tests.

​
Configure advanced settings

Configure advanced agent behavior.
Settings tab
Agent speaks first Toggle whether the agent should initiate the conversation. Max assistant turns Set the maximum number of assistant turns before ending the call. Click Save in the top right to save your configuration.

​
Next Steps

Run LLM Tests

Test your agent’s responses and tool usage

Run Simulations

Simulate conversations with the agent to identify issues before deployment