Skip to main content

Tools

Tools can enhance the capabilities of your voicebots, allowing them to execute specific tasks during a call. By integrating these tools, you can seamlessly align your voicebots with your existing workflows.

Voicebots can be equipped with embeeded tools to perform actions such as transferring calls, delegating tasks, or ending conversations appropriately. Understanding these tools and how to implement them effectively is crucial for optimizing your voicebot’s performance and ensuring a smooth user experience.

Transfer​

The Transfer tool allows the voicebot to hand over the call to specific extensions in the dialplan. This is particularly useful when complex inquiries require human intervention for better customer satisfaction.

Description

The description feature enables your voice bot to determine the appropriate moments to transfer calls. To enhance the bot's decision-making, it's essential to accurately set the description by including comprehensive information about the case.

Example:

  • If the caller requests to speak with a representative or expresses frustration, transfer the call to a human agent.
  • For billing inquiries, transfer the call to the billing department queue.
  • If the caller provides account information that cannot be verified, transfer them to the security verification IVR.

Reply Instructions

When the option Generate a reply as instructed and transfer the call after playback is selected, you can provide specific instructions that guide the model on what to say to the caller before initiating the transfer. The transfer will be executed immediately after the generated response is played back to the user, and the user will not have the option to cancel the transfer.

Example:

  • Reply "I’ll transfer you to a representative now. Please hold while I connect you."
  • Reply "I’m transferring you to our billing department. Please stay on the line."

Delegation​

This function enables our voice bots to delegate user requests to specialized bots for more accurate and efficient processing. Acting as a router, the main bot identifies the type of request and directs it to the appropriate expert bot, ensuring precise handling of areas like scheduling, support, or sales.

Pros:

  • Specialization: Delegating requests to specialized bots allows for better handling of specific domains (e.g., scheduling, technical support, sales inquiries). Specialized bots can be fine-tuned with data and responses that improve the user experience for a particular context.
  • Modularity: It creates a modular system where each bot is responsible for a well-defined area. This makes scaling easier since you can add new specialized bots without changing the main bot. Each module can be developed, tested, and optimized separately.
  • Performance: Specialized bots may offer quicker and more accurate responses for specific domains, reducing the risk of incorrect or vague answers. As they are more fine-tuned to specific requests, their performance could significantly improve compared to a generalized bot.
  • Simplified Routing Logic: The main voice bot acts as a router, which simplifies its role. It only needs to determine the type of request and route it, meaning it can focus purely on classification and routing tasks without worrying about domain-specific responses.

Cons:

  • Latency: There may be additional latency introduced if routing through multiple layers. The main bot has to recognize the request, forward it to a specialized bot, and wait for a response before delivering it to the user.
  • Complexity: Properly routing requests to the correct specialized bot could get complex, especially when user requests fall into gray areas or cross multiple domains. Misclassification could lead to frustration or incorrect responses.

Considerations:

  • Fallback Mechanism: What happens if a specialized bot can’t handle the request? It’s essential to design a fallback strategy, where the main bot either takes over again or provides the user with guidance.
  • User Experience: To ensure a cohesive experience, standardizing response structures and tones across all bots is key.
  • Delegation Limits: Delegation is limited to 3 transitions per response. This ensures efficiency and prevents excessive resource consumption.
  • Circular Delegation Prevention: Bots must avoid delegating requests back to the original voice bot or creating circular delegation paths by referring to each other. The system will detect such scenarios and stop processing the request.

Wait​

The Wait tool allows the voicebot to bypass its response and wait for the next user input if it detects that the user has not fully completed their statement. This ensures that the bot does not interrupt or misinterpret partial information, leading to a smoother conversation flow.

Description

By setting a custom description, you can guide the voicebot to make more effective decisions regarding when to wait for additional user input. This ensures that the bot remains silent until all information has been provided by the user, reducing the chances of miscommunication or incomplete responses.

Example:

  • If the user pauses while giving an address, wait for them to finish before responding.
  • If there’s background noise or the user is interrupted, wait for them to resume speaking.

Hangup​

The Hangup tool enables the voicebot to end the call once the conversation has concluded or if the user explicitly requests to end it. This enhances the user experience by allowing smooth and timely disconnection.