Sergey Galchenko, Chief Technology Officer, IntelePeer – Interview Series

What initially attracted you to the sphere of computer science and AI?

I enjoy solving problems, and software development permits you to do it with a really quick feedback loop. AI opens a brand new frontier of use cases that are hard to unravel with a standard deterministic programming approach, making it an exciting tool within the solutions toolbox.

How has AI transformed the landscape of customer support, particularly in automating CX (Customer Experience) operations?

Generative artificial intelligence is revolutionizing the contact center business in unprecedented ways. When paired with solutions that help automate communications, generative AI offers latest opportunities to boost customer interactions, improve operational efficiency, and reduce labor costs in an industry that has develop into fiercely competitive. With these technologies in place, customers can profit from highly personalized service and consistent support. Businesses, concurrently, can contain calls more effectively and battle agent turnover and high emptiness rates while allowing their employees to concentrate on high-priority tasks. Finally, gen AI, through its advanced algorithms, enables businesses to consolidate and summarize information derived from customer interactions using multiple data sources. The advantages of utilizing those technologies within the CX are clear – and there may be increasingly more data supporting the case that this trend will impact increasingly more corporations.

Are you able to provide specific examples of how IntelePeer’s Gen AI has reduced tedious tasks for customer support agents?

The final word goal of IntelePeer’s gen AI is to enable complete automation in customer support scenarios, reducing reliance on agents and leading to as much as a 75% reduction in operation costs for the shoppers we serve. Our platform is capable of automate as much as 90% of a corporation’s customer interactions, and we’ve collectively automated over half a billion customer interactions already. Not only can our gen AI automate manual tasks like call routing, appointment scheduling, and customer data entry, but it may well also provide the self-service experiences customers increasingly demand and expect—complete with hyper-personalized communications, improved response accuracy, and faster resolutions.

Are you able to describe why AI-related services must balance creativity with accuracy.

Balancing creativity with accuracy and predictability is critical in terms of fostering trust in AI-powered services and solutions—one in every of the most important challenges surrounding AI technologies today. At the start, it should go without saying that any AI solution should strive for the very best level of accuracy possible as to offer the best outputs needed for all inputs. But creating an excellent experience with AI goes beyond just providing the right information to end-users; it also includes enabling the right of that information to them, which takes an honest amount of creativity to execute successfully. As an example, in a customer support interaction, an AI-driven communications solution should find a way to routinely match the tone of the shopper and adjust as needed in real time, giving them exactly what they need in the way in which that can best reach them at that moment. The AI must also communicate in a life-like manner to make customers feel more comfortable, but not a lot as to deceive them into pondering they’re chatting with a human once they’re not. Again, all of it goes back to fostering trust in AI, which can eventually result in much more widespread adoption and use of the technology.

What role does data play in ensuring the accuracy of AI responses, and the way do you manage data to optimize AI performance?

Good data creates good AI. In other words, the standard of the information that’s fed into an AI model correlates directly with the standard of the data that model produces. In customer support, customer interaction data is the important thing to finding gaps in the shopper journey. By digging deeper into this data, organizations can begin to higher understand customer intents after which use that information to streamline and improve AI-driven engagement, transforming the general customer journey and experience. But organizations should have the best data architectures in place to each process and extract insights from the huge amounts of information related to AI solutions.

The IntelePeer AI solution uses the content and context of the interaction to find out the very best plan of action at every turn. During an interaction, if a matter is posed by the shopper that requires a solution specific to a business’s process, rules, or policies, the AI workflow routinely leverages a knowledge base that features such business data as FAQ documents, agent training materials, website data, policy, and other business information to reply accordingly. Similarly, if a matter or a request is made that the business doesn’t want AI to answer directly, the AI workflow will escalate the query to a human agent if required. The remaining interaction will be routinely added to the Q&A pairs to boost responses in subsequent customer interactions or handed off to a supervisory authority for approval prior to incorporation.

With AI’s increasing role in customer support, how do you foresee the role of frontline agents evolving?

We at IntelePeer envision a drastic reduction within the reliance on frontline agents attributable to the evolution of AI technologies. With massive strides in AI-driven call containment, which continues to enhance in quality and grow in volume, organizations today are capable of automate as much as 90% of their customer interactions. This permits them to optimize their frontline staffing and save significantly on operational costs—all while providing higher experiences for the shoppers they serve.

While some tasks are automated, which expert CX roles do you suspect will remain critical despite AI advancements?

While AI will cut down on the variety of frontline agents needed in customer support roles, a human element will all the time be needed in CX operations. For instance, AI-powered communications models have to be trained, configured, and managed with human oversight to make sure accuracy and the elimination of any biases. The human touch can also be needed to align automated customer communications with the messaging and personality of the organization or brand they’re coming from, which contributes to customer comfortability and helps to foster trust within the technology. These more technical, AI-oriented roles will overtake typical frontline roles within the years to return.

AI hallucinations are a priority in maintaining accurate customer interactions. What specific guardrails has IntelePeer implemented to stop AI from fabricating facts?

 Businesses have to implement generative AI today to remain relevant amid the continuing revolution while avoiding a rushed and disastrous rollout. To be able to try this responsibly, corporations must start with implementing a Retrieval Augmented Generation (RAG) pattern to assist their gen AI interface with analyzing large enterprise datasets. For automated customer support interactions, brands must create a human feedback loop to investigate past interactions and improve the standard of those datasets used for fine-tuning and retrieval augmentation. Further, as a way to eliminate AI hallucinations, organizations needs to be laser focused on:

• implementing guardrails by analyzing customer interaction data and developing comprehensive, dynamic knowledge bases;
• investing in continuous monitoring and updating of those systems to adapt to latest queries and maintain accuracy; and
• training staff to acknowledge and manage unidentifiable permutations ensures seamless escalation and backbone processes.

How do you be sure that large language models (LLMs) interpret context appropriately and supply reliable responses?

 A haphazard approach to implementing gen AI may end up in output quality issues, hallucinations, copyright infringement, and biased algorithms. Due to this fact, businesses have to have response guardrails when applying gen AI in the shopper service environment. IntelePeer utilizes retrieval augmented generation (RAG), which feeds data context to an LLM to get responses grounded in a customer-provided dataset. Throughout the complete process, from the moment the information gets prepared until the LLM sends a response to the client, the obligatory guardrails prevent any sensitive information from being exposed. IntelePeer’s RAG begins when a customer asks a matter to an AI-powered bot. The bot performs a lookup of the query within the knowledge base. If it cannot find a solution, it’ll transfer to an agent and save the query to the Q&A database. Later, a human will review this latest query, conduct a dataset import, and save the reply to the knowledge base. Ultimately, absolute confidence goes unanswered. With the RAG process in place, businesses can maintain control over response sets for interaction automation.

Looking ahead, what trends do you anticipate in AI’s role in customer experience?

At IntelePeer, we deeply imagine that generative AI is a strong tool that can positively augment human communication capabilities, unlocking latest opportunities and overcoming long standing barriers. AI will proceed enhancing customer support communications by streamlining customer support interactions, offering around-the-clock assistance and providing language-bridging capabilities. Furthermore, trained on large language models (LLMs), virtual assistants will find a way draw upon hundreds of thousands of human conversations to quickly detect emotions to change its tone, sentiment and word selection. There shall be increasingly more evidence that companies that successfully use AI to boost human connections experience see a big return on investment and improved efficiency and productivity.