Conversational commerce unicorn Gupshup has launched Auto Bot Builder, a tool that harnesses GPT-3 to automatically build advanced chatbots tailored to enterprise requirements.
Auto Bot Builder leverages the GPT-3 LLM (Large Language Model) and fine-tunes it using proprietary enterprise knowledge base and domain expertise — resulting in a chatbot specialised to an enterprise, unlike ChatGPT, which is a general-purpose chatbot.
This, the company says, will enable enterprises to incorporate the latest advances in AI technology, in a no-code environment, into their conversational experiences to substantially enhance their customer engagement. It reduces the time and effort taken to create conversational journeys, enabling enterprises to develop more journeys faster for use cases across the entire customer lifecycle.
Beerud Sheth, CEO of Gupshup, told businessline, “The new capability amplifies and accelerates the benefits of the present use cases provided by the company. From customer support and troubleshooting to upselling and cross-selling, it can handle everything. The offering can be adopted by enterprises across verticals according to its needs, we think quick and increased adoption will be seen by the BFSI sector.”
With the Auto Bot Builder tool, a user can instantly build a chatbot using content from their website, documents, message logs, product catalogs, database, and other corporate systems of record. The tool accepts content of any size, processes it and fine-tunes the LLM to the specific context. Auto Bot Builder is capable of handling really large content sets, which need special pre-processing, said the company.
Furthermore, Gupshup has also developed fine-tuned instances of industry-specific models based on its proprietary training data and domain expertise that provides a head-start in developing high-quality enterprise-specific conversational experiences.
Built on LLMs, these chatbots demonstrate a high degree of language capability that engages the end user. They can handle virtually any natural language query posed by the user and provide meaningful responses in almost all scenarios. Businesses can build these chatbots for each stage of the customer lifecycle including marketing, commerce and support, said the company.
Comments
Comments have to be in English, and in full sentences. They cannot be abusive or personal. Please abide by our community guidelines for posting your comments.
We have migrated to a new commenting platform. If you are already a registered user of TheHindu Businessline and logged in, you may continue to engage with our articles. If you do not have an account please register and login to post comments. Users can access their older comments by logging into their accounts on Vuukle.