Join top executives in San Francisco on July 11-12 to hear how leaders are integrating and optimizing AI investments for success.. Learn more
Customer Experience (CX) Solutions Platform simplr today announced the launch of Cognitive Paths, a new generative artificial intelligence technology with comprehensive safeguards to improve customer service interactions. By incorporating OpenAI’s ChatGPT into its platform, Simplr’s Cognitive Paths enables customer service organizations to fully harness the power of Long Language Models (LLMs) and generative AI while eliminating customer experience risks. customer and brand reputation.
The solution reduces the overall volume of information available to the LLM-powered chatbot and eliminates the possibility of hallucinations, i.e. engaging in off-brand topics. In addition, enterprise-grade security protocols ensure that no data is transferred to any publicly available LLM, thus protecting sensitive client data.
“Simplr’s Cognitive Paths works by generating unique and proprietary data sets for each client,” Eng Tan, CEO and founder of Simplr, told VentureBeat. “The result is an extensive curated knowledge base, but a much more specific and personalized set of data than ChatGPT has access to on its own. Cognitive Paths then instructs the LLM to only extract information from certain data sets based on the nature of each unique customer interaction. The result is the power of generative AI without the hallucinations.”
Simplr has curated an extensive knowledge base consisting of data sets such as knowledge base content, product warranties, top-rated human resolutions, brand policies, and their own experience in the customer support and service space. This knowledge base is more specific and personalized compared to the data that ChatGPT has access to on its own.
“Using the combined power of LLM with Simplr’s extensive curated dataset of what makes great customer service interactions in the industry, we are now able to essentially automate that first-rate experience for our customers across a wide range of customer service inquiries,” Tan said. “The result is a better brand reputation, more returning customers, and more revenue generated through customer service than ever before.”
The company views the launch of Cognitive Paths as a significant milestone in the customer service industry. He believes this technology will allow companies to automate complex inquiries, deliver superior customer experiences, and gain a competitive advantage over their peers.
“Other chatbot vendors have historically focused on simple transactional questions that typically require one or two steps to complete,” Tan said. “With Cognitive Paths, we’ve injected our expertise into more complex human interactions, especially in help desk. It means that we can now automate, through LLM, those kinds of questions that are still out of reach for other chatbot providers.”
Eliminate hallucinations to provide true knowledge
according to a Juniper Research study, AI will automate 70% of customer inquiries by the end of 2023. However, using generative AI in customer interactions also carries risks that can damage brand reputation and customer relationships if not are managed properly. Generative AI can often generate irrelevant content and engage in off-brand topics, making it risky to use.
“The main philosophy behind Cognitive Paths is database segregation for security. Generative AI technologies are mind blowing because of the amount of data they have access to. Out of the box, large language models (LLMs) cannot autonomously discern levels of accuracy and authenticity from knowledge bases, which can result in incorrect or nonsensical answers,” Tan told VentureBeat.
Simplr’s new suite of security measures includes OpenAI’s ChatGPT and a set of AI training parameters to guide the chatbot technology towards correct client resolution without the risk of hallucinations. This addresses the potential risk of negative impacts on brand reputation and customer relationships arising from generative AI in customer interactions.
Cognitive Paths uses enterprise-grade security protocols to ensure that there is no data transfer to any publicly available LLM, thus eliminating the risk of revealing PII or sensitive client data. Additionally, by leveraging data accumulated from Simplr’s history of optimizing its outsourced human workforce, Cognitive Paths significantly expands the range of customer interactions that can be effectively resolved through automation.
“Using generative AI in customer-facing situations without proper security measures is a recipe for a public relations or security disaster. At the same time, it can open up the responsibility for data security,” Tan explained. “On the customer service front, using uninhibited LLMs means that it also opens up a very real risk that sensitive customer data could also be exposed. Therefore, in addition to data restriction, we have implemented enterprise-grade security protocols in Cognitive Paths, which prevent PII or sensitive customer data from being re-shared in LLM data sets.”
Tan said his company has been dedicated from the beginning to understanding the range of multi-shift queries that humans can respond to. This covers a broader and more varied set of inquiries than is typically addressed by conventional chatbot technology providers.
In addition, it covers complex support scenarios, as well as upsell and cross-sell actions.
“Other chatbot providers have always thought ‘What can be diverted?’ Meanwhile, Simplr has always been focused on ‘What can be solved?’ ‘What replicates the best human agents?’ That is what gives us a clear advantage in the customer service generative AI race,” he said.
Leverage OpenAI models to improve customer interactions
The platform leverages the generative capabilities of GPT-4 to improve customer interactions.
According to Tan, LLMs can now summarize large amounts of unstructured data, which was impossible with previous NLP technologies. Clients often include superfluous or irrelevant information in their inquiries, but LLMs can sift through this noise to identify the real problem and succinctly summarize it for client confirmation before proceeding. This feature also has significant applications in agent support tools.
“We are especially excited about GPT-4’s multimodal capabilities, such as image recognition. This is a big step forward in terms of engaging customers through chat.
“But again, think about technical troubleshooting,” he added. “Now, by determining the make and model of a particular device, a customer can simply take a photo and send it to the bot. Previously, the customer would have to take some time to find that information, be it on the device itself, in the user manual, in the product information online, etc.
He argues that while LLMs can add personality to other chatbot offerings or help locate the right answer more quickly, they don’t fundamentally expand the range of tickets that can be automated. In contrast, with Cognitive Paths, users can now automate much more complex, multi-turn queries.
“Think warranty and insurance claims, technical support or automated product inquiries for large retailers and OEMs with a large number of products. One of the things I’m most excited about is the ability to automate conversational commerce,” Tan said. “This will make it much easier and more cost-effective for customer service teams to start generating revenue than in the past.”
Regarding the security of customer data, Tan emphasized that Simplr has always handled customer and consumer data with the utmost care. The company has implemented enterprise-grade security protocols to ensure the safety of sensitive customer data and personally identifiable information (PII).
“We leverage a wealth of tools and protocols from Microsoft Azure, dedicated environments, and our parent company, Asurion, to maintain the highest possible standards for enterprise security,” Tan explained.
What’s next for Simplr?
Tan believes that AI is revolutionizing customer service and that no aspect of a business will be more influenced by AI than customer service and experience. The archaic call center and BPO models of the past are not fit for a digital and automated future.
“Everyone has had that experience with a top notch customer service agent. They are friendly, talk to you like a human being, and can resolve your issue quickly. But unfortunately, the vast majority of customer service inquiries are forgettable at best, and in most cases frustrating and time consuming,” she said. “When we started Simplr, we set ourselves a simple mission: “How can we scale top-tier customer service interactions?” And we built a platform that made each of our human agents the best possible agent for our clients at any given time.”
He explained that Simplr envisions the future of customer service as a seamless integration of all aspects of the customer experience related to support interactions. The company plans to harness the incredible power of generative AI to deliver equally exceptional experiences, whether customers are interacting with a bot or a human, and even during in-person support interactions.
“The platform we’ve built enables this integrated experience for customers across the support spectrum,” Tan added. “As far as we’ve come since the launch of ChatGPT last fall, this is just the beginning. There’s so much white space about where we can collectively take the customer experience for the rest of the decade. Simplr will play a leadership role in facilitating that change.”
VentureBeat’s mission is to be a digital public square for technical decision makers to gain insights into transformative business technology and transact. Discover our informative sessions.