Back to list
Simulation Testing Now Live for All Agents

Simulation Testing Now Live for All Agents

We’ve launched Simulation Testing for both single and multi-prompt agents!

Now, instead of manually typing inputs, you can write a user prompt to quickly simulate a full conversation.

We’ve also added Batch Simulation Testing, so you can run multiple test cases at once with ease.

More System Default Dynamic Variables

More system default dynamic variables, currently support:

  • {{current_time}}: current time in America/Los_Angeles (Monday, March 24, 2025 at 02:53:01 PM PDT)
  • {{current_time_[timezone]}}: current time in given timezone
  • for example: current_time_Australia/Sydney, current_time_America/New_York
  • {{call_type}}: web_call or phone_call

For Phone calls only:

  • {{direction}}: inbound or outbound
  • {{user_number}}: user phone number (inbound: from_number, outbound: to_number)
  • {{agent_number}}: agent phone number (inbound: to_number, outbound: from_number)

Default Value for Dynamic Variables

Add a default value for dynamic variables across all endpoints if they are not provided.

Inbound Call Webhook

If you want to use different agents under the same inbound phone number, such as setup a daytime agent and a afterhour agent, or route to different agent based on the incoming phone number.

This is now possible with the Phone Inbound Webhook.

Better Accuracy? Try GPT-4o for Post-Call Analysis

We’ve added more LLM options for post-call analysis.

If you find the default analysis isn’t accurate, feel free to switch to GPT-4o.

Once selected, GPT-4o will be charged at $0.017 per session.

If you choose GPT-4o Mini, post-call analysis remains free.

Organize Your Agents with Folders

To better manage demo and production agents, you can now organize them using folders.

If you prefer not to use this feature, simply collapse the folder view.