# Caller Identification {% hint style="info" %} *Use this template when you want to add an additional layer of security to your agent with the **identification and verification** of the caller.* {% endhint %} To use this template, simply choose it from the templates page when you create a new agent. You can then make changes to customize it based on your business needs. ![](https://3877181490-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-L_81A0PNZfdawu_TPAO%2F-Mb29qruY48cT1A3pWcW%2F-Mb2CGJgK_DnMqkAbiI3%2FScreen%20Shot%202021-05-31%20at%2019.14.53.png?alt=media\&token=dacbce92-a4ac-435a-b293-d51a2cb8dae4) ### Flow Overview #### Step 1 - Starting the Conversation We start with a *Speak* node introducing the company to the caller. Using the *Speak* node we don't expect any input from the caller in this node. #### Step 2 - Collect First Identification Parameter The *Speak* node is followed by a *Collect Input* node collecting the first identification parameter, e.g. a caller-specific identification number. In case we can't collect the ID, the agent will route the call to a live representative. Therefore, the *No Input* and *Missed* tabs are connected to a *Speak* node, notifying the caller that in this case the call is being routed, followed by the *Route Call* action node. #### Step 3 - ID Confirmation & Verification Once the ID is collected, the agent is going to read it out to the caller for confirmation in the following *Collect Input* node. The *Conditions* node will classify based on the caller's response. If the ID is correct, the agent will send the ID via the *Webhook* node to the third-party service in order to verify the caller with the CRM. If incorrect, the agent will prompt the caller to give the ID number again. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://studio.docs.ai.vonage.com/ai-studio/templates/identification-and-verification.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.