Designing AI Voice Bots For Our Clients' Success In Singapore

Key Factors AI Voice Bot Needs For A Natural and Engaging Conversation in Singapore.

In Singapore, AI voice bots is still considered as a new technology for sales & customer-centric activities. However, the demand for this technology is increasing as the government and business owners seek to move towards Digital Transformation. Currently, the AI voice bots are commonly used to assist our clients by conversationally guiding customers to meet some of their business or sales objectives. In order to achieve these goals, our AI voice bots need to have ‘smart’ (intuitive), smooth, seamless ‘conversations’ with customers. Our programming and integration need to be sophisticated and nuanced. Technology needs to be cutting edge, or else they are likely to fall short and create customer frustration.

1. Creating Intent: Understand Meaning

This is perhaps the most essential criteria. Meaning and comprehension is everything during a conversation. Sadly, as human beings, we aren’t always literal or to the point when we speak. Given this inherent human irony, a bot should be able to use its ‘Intent Ability’ feature to extract the meaning behind our words.

For example, the intent behind a "ya", "can", "ok lor", “sure” or “why not” is most likely a “yes”. Conversely, “I don't think so”, “It's ok” and “not really”, likely translates to a “no”. These examples show that a voice bot or chat bot’s job is not straightforward. Today, as companies in Singapore starts to adopt the Digital Transformation Journey, AI chatbots or voice bots is one of the methods to reduce low value job tasks.

However, we have to make sure our voice bots or chats bots has nothing is lost in translation.

To enable a successful transition to automation, voice bots need to be smart to carry out convincing conversations. They need to understand if they’ve reached the right person, they need to understand the sentiment of the person and act accordingly (e.g. schedule a call later or book an appointment or transferring calls, etc.). Here are some scenarios to provide more context:

Scenario 1: When the customer who receives a call is unable to speak and hangs up very quickly after a few words.

AI Voice Bot: “Hello, good day to you. I am making this call is regarding your credit card payment for July 2021. Am I speaking with Mr. Y?”

The answer to this seemingly simple question isn’t as clear-cut as we may think. Answers may have a range:

Objections word(s)

“I’m busy.”

“I’m driving. Call me later.”

“I am not free now.”

“Call me again later.”

Or (hopefully), “Yes”, "oh ok"

In all the above responses (except for the last one), the AI voice bot’s task is challenging. It needs to determine that the caller is unavailable for different reasons and that the call needs to be rescheduled. A smart AI voice bot or AI chatbot would politely thank the person on the other line and ends the call. Another designing thought would be to be mindful of the customer’s request, and our back-end system will schedule a call to follow up.

Scenario 2: When the customer’s answer has multiple steps

AI Voice Bot: “Hello, good day to you. I am making this call is regarding your credit card payment for July 2021. Am I speaking with Mr. Y?”

Customer: “Mr. Y, speaking. I’m busy. Call me back again in the evening.”

Here the AI voice bot or chatbot needs to comprehend and act upon 3 steps all in one go without having to repeat the question:

2. The Ability To Pause, Listen & Interrupt

The first point around intent comprehension makes it clear that the standards set for machine programmed assistants like chatbots and voice bots is rather high. While we want the bot to be a ‘good listener’ so it can determine next steps, or pause when the person on the other end is talking, we also want the bot to be able to make the reason of its call very clear.

For example, AI voice bots are frequently used to apprise clients of some important information or remind them of say, a timeline. A good bot design would be one where the bot is programmed to not pause during that time when it’s providing critical information, even if it is interrupted. So as to make the intent of the call clear.

As illustrated in this article, AI voice bots can be a huge value-add in any customer engagement process. However, they are here to assist and not replace core human-to-human interaction. In fact, employees can go through job design process to obtain a career development pathway and better remunerations.

3. Streaming Recognition

As with all technology, speed is essential for a pleasant, efficient experience. A good voice bot should, therefore, be able to interpret and act at the same rate at which the customer speaks. Lags and slow responses cause frustration and create a poor impression of the business.

4. Personalization

When a customer calls a business they would expect fast responses. This would mean resolving their their problems as soon as possible. Optimal integrations and programming should ensure that the bot greets the caller by name, knows caller history, picks up the likely reason for the call based on current and past calling patterns. Most importantly, a good voice bot should be able to personalize suggestions based on this type of customer knowledge.

5. Access to Human Employees

AI Voice bots are there to assist employees in meeting customers’ needs. They are not there to replace agents. At any time during a call, the customer should have the option to speak to a human employee. For instance, if the bot can’t understand the customer’s issue within a single question, the customer or caller should be redirected to a human employee on priority. The last thing a customer wants is to be stuck with a AI voice bot that goes on a mindless loop without resolving their queries.

6. AI Machine Learning - Continuously Learn

Understanding human speech is a ongoing process. Even for us humans, how often do we misunderstand the other party's conversation and meaning? As as result, there is a need for our AI voice bot to continuously improves accuracy and predictability based on previous results. Currently, our AI voice bots are able to identify key words, parse long sentences, most importantly.. understand Singlish!