HP rolls out AI-powered ‘virtual agent’ to solve customer queries

Anand Subramaniam is SVP Global Marketing for eGain Corp. eGain’s solution automates digital-first customer engagement for global brands. The chatbot market is expected to grow in value from $703 million in 2016 to $3,172 million by 2021, according to MarketsandMarkets. New research from Juniper expects chatbots to be responsible for over $8 billion a year in cost savings for organizations by 2022. Interactive voice responses (IVRs) struggle here as well — they often lead to conversational cul-de-sacs that cause you to keep making U-turns.

Digital Journal

• Ask for a no-risk, no-charge production pilot to see if you like your experience with the technology. When employees swap the office for a more relaxing setting, it can expose enterprises to additional cybersecurity risks. Do you remember how many times you went into a bank for service in the last several years? ATMs virtually eliminated the need to go inside a bank, and mobile banking has taken it one step further by eliminating the need to even go to the ATM.

• A chatbot is a computer program designed to simulate conversation with human users.
• It parses the customer’s query to understand what they’re asking, before searching for the answer in its catalogue of support documents.
• Interactive voice responses (IVRs) struggle here as well — they often lead to conversational cul-de-sacs that cause you to keep making U-turns.

The “solve” phase may entail finding the answer needle in a document haystack or going through a self-service conversation with the customer to resolve an issue. It is like what a doctor might do in the case of a diagnosis or what an expert advisor might do in the case of a product recommendation. When it’s not done well, this can lead to a phenomenon called tech support rage, as the New York Times so eloquently articulated (paywall). The virtual agent is built with Microsoft-developed AI technology that was first piloted on the company’s campus. When Porter-Ainer visited Microsoft, the bot’s engineers approached her about deploying it to HP’s support centres.

Extreme weather misinformation ‘putting lives at risk,’ study warns

The digital agent is capable of automatically detecting spelling mistakes and interpreting the intended meaning. HP’s friendly and conversational bot is meant to provide customers with a faster self-service alternative to waiting for a human support employee to become available. The agent appears at the bottom-right of HP support webpages, using a similar presentation to the live chat popups on many other websites. While a customer service chatbot is not the newest of ideas, the HP agent learns “independently” whenever it completes a new chat with a user. As more users engage with the bot, it can construct additional help and guidance to answer future queries with more precision. • Always provide a safety net of human-assisted service, but make sure that customers can escalate to human assistance without having to repeat the context they’ve already provided.

HP said the agent’s already cutting down customer waiting times, however, it has not released details of those efficiencies. With the bot able to takeover handling of basic queries, staff will be freed up to focus on more complex issues. A chatbot is a computer program designed to simulate conversation with human users. Chatbots can be deployed over text message, as pop-ups on websites or via messaging apps, like Facebook or WhatsApp. Use the 80/20 rule to prioritize the scope of knowledge you use to answer customer questions, starting with the most common customer queries first.

The agent learns “independently” whenever it completes a new chat with a user. This allows it to add it to its “core knowledge” of 50,000 pages of HP product information. It’s meant to provide customers with a faster self-service alternative to waiting for a human support employee to become available. It parses the customer’s query to understand what they’re asking, before searching for the answer in its catalogue of support documents. If it’s unable to resolve the problem, it’ll automatically hand over to a human operator.

Extreme weather misinformation ‘putting lives at risk,’ study warns

Although the bot’s still technically in an investigative phase, Porter-Ainer said it’s already meeting its design requirements. The solution is to make sure your self-service system is backed by a knowledge management system that can drive a conversation with the customer and ask clarifying questions where needed. Many self-service systems do a poor job of understanding customer intent, as is evident through the examples I provided earlier. They just know what the symptom is and express it in different ways, which are called “utterances” in tech parlance. Ask potential solution partners how their tools map utterances to true intents and go on to solve problems.

Self-service can happen at many touchpoints — including an IVR, website, mobile app, messaging function, chat box and so on. Point products support specific channels, often just one, for connecting with the customer. And do-it-all toolkits, while they check all the boxes in some cases, often fail to take advantage of the richness of individual touchpoints. Ask potential solution partners how deeply they support individual touchpoints and how easy it is to add new touchpoints. Legacy self-service systems often throw FAQ lists or encyclopediac documents at the customer and do not give them the exact information they need. Or, the self-service system transfers them to human agents, often without retaining the context of their inquiry.