Join top executives in San Francisco July 11-12 to hear how leaders are integrating and optimizing AI investments for success. Learn more
Customer Experience (CX) Solutions Platform. Simple today announced the launch of Cognitive Paths, a new generative AI technology with comprehensive protections to improve customer service interactions. By incorporating OpenAI’s ChatGPT into its platform, Simplr’s Cognitive Paths enables customer service organizations to harness the full power of large language models (LLMs) and generative AI while eliminating risks associated with customer experience and reputation of the brand.
The solution reduces the overall volume of information available to the LLM-powered chatbot and eliminates the possibility of hallucinating, i.e. engaging in off-brand topics. Additionally, enterprise-grade security protocols ensure that no data is passed back into any publicly available LLM, thus safeguarding sensitive client data.
“Simplr’s cognitive journeys work by generating unique, proprietary datasets for each customer,” Eng Tan, CEO and founder of Simplr, told VentureBeat. “The result is a large curated knowledge base, but a much more focused and personalized data set than ChatGPT has access to on its own. Cognitive Paths therefore directs the LLM to extract information only from certain datasets 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 datasets such as knowledge base content, product collateral, high-level human resolutions, brand policies, and its own experience in the customer support and service space. This knowledge base is more targeted and personalized than the data ChatGPT has access to on its own.
“Using the combined power of the LLM with Simplr’s large curated dataset on what makes customer service interactions great in the industry, we can now essentially automate that top-notch experience for our customers across a broad range of customer service inquiries,” said Tan. “The result is 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 enable companies to automate complex requests, deliver superior customer experiences, and gain a competitive edge over their peers.
“Other chatbot vendors have historically focused on easy, transactional questions that usually take a step or two to complete,” Tan said. “With Cognitive Paths, we have injected our experience of more complex human interactions, especially in technical support. It means we can now automate, via LLM, those types of questions that are still outside the purview of other chatbot providers.”
Eliminate hallucinations to provide true insights
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 handled correctly. Generative AI can often generate irrelevant content and engage in off-brand topics, making it risky to use.
“The core philosophy behind Cognitive Paths is database segregation for security. Generative AI technologies are hallucinated because of the amount of data they have access to. Out of the box, large language models (LLMs) are unable to autonomously discern the levels of accuracy and authenticity of knowledge bases, which can lead to incorrect or nonsensical answers,” Tan told VentureBeat.
Simplr’s new set of security measures includes OpenAI’s ChatGPT and a set of AI training metrics to guide the chatbot technology towards successful customer resolution without the risk of hallucinations. This addresses the potential risk of negative brand reputation and customer relationship impacts from generative AI in customer interactions.
Cognitive Paths employs enterprise-grade security protocols to ensure there is no reverse data transfer in any publicly available LLM, thereby eliminating the risk of disclosing personal information or sensitive client data. Additionally, by leveraging the 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 the proper safeguards is a recipe for a public relations or security disaster. At the same time, it can open up data security accountability,” Tan explained. “On the customer service front, using uninhibited LLMs also opens up a very real risk that even sensitive customer data can be exposed. In addition to data restriction, we have implemented enterprise-grade security protocols in Cognitive Paths, which prevent the sharing of PII or sensitive customer data in LLM data pools.”
Tan said his company has been dedicated from the beginning to understanding the range of multi-shift requests that humans can respond to. This encompasses a broader and more diverse set of demands than those typically faced by conventional chatbot technology providers.
It also covers complex technical support scenarios as well as upsell and cross-sell actions.
“Other chatbot providers have always thought ‘What can be diverted?’ Meanwhile, Simplr has always focused on “What can be fixed?” “What does the best human agents replicate?” This is what gives us a distinct advantage in the race for generative customer service AI,” he said.
Leverage OpenAI models to improve customer interactions
The platform leverages the generative capabilities of GPT-4 to enhance customer interactions.
According to Tan, LLMs can now summarize large amounts of unstructured data, something not possible with previous NLP technologies. Clients often include extraneous or irrelevant information in their inquiries, but LLMs can resolve this noise to identify the actual problem and briefly summarize it for client confirmation before proceeding. This feature also has significant applications in agent support tools.
“We are particularly excited about the multimodal capabilities of GPT-4, such as image recognition. This is a big step forward in terms of customer engagement via chat.
“But, again, think about technical troubleshooting,” he added. “Now, to determine the make and model of a particular device, a customer can simply take a picture of it and send it to the bot. Previously, the customer would have had to take some time to find this information on the device itself, in the user manual, online product information, etc.”
He argues that while LLMs can add personality to other chatbot offerings or help pinpoint the correct answer faster, they don’t substantially expand the range of tickets that can be automated. Conversely, with Cognitive Paths, users can now automate much more complex, multi-shift requests.
“Think of warranty and insurance claims, technical support, or automating product inquiries for large retailers and OEMs with a plethora of products. One of the things I’m most excited about is the ability to automate conversational commerce,” said Tan. “This will make it much easier and cheaper for customer service teams to start generating revenue than in the past.”
Regarding the security and protection 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 are leveraging a variety of tools and protocols from Microsoft Azure, dedicated environments, and our parent company, Asurion, to maintain the highest possible standards for corporate security,” Tan explained.
What is the future of Simplr?
Tan believes AI is revolutionizing customer service and that no aspect of a business will be impacted by AI more 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 solve your problem quickly. But, unfortunately, the vast majority of customer service inquiries are forgettable at best and very often frustrating and slow,” she said. top-notch customer service?” And we’ve built a platform that has turned each of our human agents into the best possible agent for our clients at any given moment.”
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 great experiences whether customers interact with a bot or 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. “Despite how far we’ve come since launching ChatGPT last fall, this is just the beginning. There’s so much white space for where we can collectively take the customer experience into the rest of the decade. Simplr will play a leading role in facilitating this change.”
VentureBeat’s mission it is to be a digital city square for technical decision makers to gain insights into transformative business technology and transactions. Discover our Briefings.