Cyara has integrated OpenAI’s GPT-3 to improve the quality and development of conversational AI.
GPT-3 will speed up the creation of training and testing data for Cyara Botium, the company’s conversational AI testing and assurance solution.
Cyara describes itself as the “leader and creator of the CX Assurance category”, providing assurance to multiple communications channels, including voice, video, chatbot, and WebRTC.
Christoph Börner, Senior Director, Digital at Cyara, said: “Cyara is leading the charge in delivering exceptional conversational AI experiences by recognizing the power of large language models (LLMs).
“This integration is another example of our commitment to delivering cutting-edge chatbot testing solutions to our customers.
“Cyara’s integration of GPT-3 for training and testing conversational AI has not only elevated the industry standard for delivering exceptional chatbot experiences but has also played a pivotal role in shaping the future of CX.”
In order to test and train chatbots, organisations must locate a number of means by which users can communicate their intent while engaging with a chatbot or voicebot.
Finding numerous ways for users to communicate their objectives is made more difficult by the unlimited and unpredictable options that users have.
If a customer wants to check their bank account balance, for example, they could phrase it in a variety of ways, such as: “What is my balance?”, “How much money do I have?”, “Check balance”, and so on.
A high-quality, rigorously tested chatbot should be able to understand all of these inputs.
Without undertaking the necessary training and testing on an exhaustive set of data, chatbots will be less likely to recognize what the user has said.
It will, therefore, be unable to resolve customer issues, resulting in a poor experience.
According to a recent Forrester study commissioned by Cyara, 61 percent of consumers believe chats are frequently unable to understand what they have said.
Negative chatbot experiences are damaging brands’ reputations and finances, according to Cyara, whereas positive experiences can have the opposite effect.
Key Enterprise Benefits
Through a combination of GPT-3 LLM and the domain that the chatbot is associated with, Cyara Botium is able to automatically generate a list of user examples.
When the list of user inputs has been created, it can then be used for training and testing, which can add value to companies in three key ways.
First, it reduces the time to develop training and testing data.
Second, it cuts back on the amount of labor and costs needed to develop and test a chatbot.
Finally, it improves the chatbot’s quality by adding test coverage.
Cyara’s Botium’s AI-powered Data and Test Generator is now available for Cyara’s enterprise customers.
In July 2022, Cyara launched new chatbot testing features, which included AI-powered data and test generation, extended performance testing, and an interactive voice response channel and voice testing.
Shortly before this, in May 2022, Cyara acquired Botium, a no-code test automation toolset provider, to bolster its digital CX assurance capabilities.
The acquisition brought with it 1,500 customers and 185,000 open-source users to carry out over one million chatbot tests.