Observe.AI is launching products aimed at aiding contact centers. The company’s new LLM and Generative AI suite seeks to “differentiate customer experience” from conventional contact centers.
This week, Observe.AI introduced its 30-billion-parameter Contact Center LLM and new Generative AI Suite for boosting agent performance. Unlike generic models like GPT, Observe.AI says its proprietary large language model (LLM) uses a “domain-specific dataset”. This consists of hundreds of millions of customer interactions. In doing so, the company claims, it enables the models to support a diverse set of AI-based tasks that are highly specific to contact center teams.
Standard GPT does not measure up
Satarupa Chatterjee, Observe.AI’s Product Marketing Leader, detailed the new offering in a blog post. Observe.AI has built an LLM that is “completely customized” for contact center data. It has been trained to perform well for contact center use-cases. Examples include call summarization, generating coaching tips or responses to customer questions.
“Based on initial tests, our Contact Center LLM was found to be 35% more accurate than GPT3.5 in automatically summarizing conversations,” Chatterjee boasts. In addition, it will be “33% more accurate in identifying customer or agent sentiment during calls”.
A Generative AI Suite for contact centers
Observe.AI’s new Generative AI Suite “empowers agents throughout the entire customer interaction process, improving performance and productivity every step of the way”.
“Today, when a customer asks a question that isn’t very easy to answer, your agents put them on a “brief hold” to go search knowledge base (KB) articles or ask a supervisor”, she continues. With Knowledge AI, agents can type questions and get ready-to-use answers, she says.
The suite also contains the Generative AI-powered Auto Summary feature. This can supposedly “completely eliminate” the need for agents to capture notes. Generative AI can create summaries in multiple formats as well. This includes structured and unstructured summaries, and those crested based on “entities” mentioned on the call like names, phone numbers, dollar amounts, and so on.
Another feature is “Auto Coaching”, where a tool serves up auto-created feedback from Generative AI to agents so they can make quick adjustments on their own to improve their performance.
“These three new capabilities are the first step in our Generative AI journey”, Chatterjee concludes. She adds that Observe.AI plans to add new features in the coming months based on customer feedback.