### Answer You can extract a user's interest as a dynamic variable at runtime and then filter your conversation flow based on it. Retell AI supports extracting variables live during a conversation using the Extract Dynamic Variable Node. [(1) ]() This node extracts information from the conversation and stores it as a dynamic variable. According to the changelog, agents can now "extract and store dynamic variables live and mid-conversation, with reliably and accurately retrieved information." [(2) ]() Specifically, agents can: - Automatically save names, emails, budgets, and preferences - Reference collected data anytime during the call - Personalize workflows in real time The variable types you can collect include Text, Numbers, Boolean, and Enum (predefined lists like services or products) . [(2) ]() [(1) ]() Once extracted, you can use these variables in conversation flow conditions. To check if a variable is set in conversation flow equations: [(3) ]()

Equation: {{user_name}} exists
Result: True if variable is set

This feature works in single, multi-prompt, and conversation flow agents. [(2) ]() So yes, you can extract an interest variable during the conversation and use it to control transitions in your flow.

​ To learn more, see the sources I considered: [[1] Extract Dynamic Variable Node](https://docs.retellai.com/build/conversation-flow/extract-dv-node) [[2] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[3] Dynamic Variables](https://docs.retellai.com/build/dynamic-variables) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer The Extract Variables in Real Time feature was released on July 7, 2025, as part of the "Major Platform Upgrades: Knowledge base, warm transfer, Voice & Analytics" changelog entry. [(1) ]() [(2) ]()

​ To learn more, see the sources I considered: [[1] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[2] Major Platform Upgrades: Knowledge base, warm transfer, Voice & Analytics](https://www.retellai.com/changelog/major-platform-upgrades-knowledge-base-warm-transfer-voice-analytics) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer The most likely cause is a timezone mismatch. The default

{{current_time}}

variable uses

America/Los_Angeles

timezone. [(1) ]() If your actual location is in a different timezone, this could cause the date to appear off by a day (especially around midnight in either timezone) . Solution: Use the timezone-specific variable format:

{{current_time_[timezone]}}

For example: -

{{current_time_Australia/Sydney}}

-

{{current_time_America/New_York}}

Similarly, if you're using the calendar variable,

{{current_calendar}}

defaults to

America/Los_Angeles

, but you can specify your timezone with

{{current_calendar_[timezone]}}

. Make sure the timezone you specify matches where your users or business operates. The available system variables include examples like

{{current_time_Australia/Sydney}}

and

{{current_time_America/New_York}}

.

​ To learn more, see the sources I considered: [[1] Dynamic Variables](https://docs.retellai.com/build/dynamic-variables) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer --- Toronto should work. The

{{current_time_[timezone]}}

variable accepts standard timezone identifiers. [(1) ]() The format would be:

{{current_time_America/Toronto}}

The documentation shows examples like

{{current_time_Australia/Sydney}}

and

{{current_time_America/New_York}}

, which follow the standard IANA timezone database format (Region/City) . Toronto is a valid IANA timezone identifier (

America/Toronto

) , so it should work the same way.

​ To learn more, see the sources I considered: [[1] Dynamic Variables](https://docs.retellai.com/build/dynamic-variables) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.