Part 1: Meet Atom Ai – the GPT Powering Innovation at WWT
This is the first article in a series exploring the technical foundations of Atom Ai (formerly WWT GPT), a GenAI-powered chatbot developed to increase employee productivity. It focuses on the purpose, scope, data sources and framework of WWT GPT as well as feedback and next steps.
The adoption of artificial intelligence and machine learning (AI/ML) has revolutionized a wave of innovations across many industries and technical domains. Since early 2023, WWT has been developing internal applications that harness the power of generative AI (GenAI) and large language models (LLMs).
We developed an intelligent chatbot, Atom Ai (formerly WWT GPT), with the mission of increasing internal employee productivity, growing company revenue, and sparking innovation across our workforce. Atom is currently available to more than 3,500 WWT employees, and additional releases are planned for 2024.
Business understanding
The current version of Atom is built to access three main data sources for information retrieval: wwt.com, historical proof-of-concept (POC) documents, and ServiceNow records for POCs.
- wwt.com content includes articles, case studies, events, labs, white papers and more. The development team partnered with wwt.com's platform data owners and marketing leaders to shape how to best extract business and technical insights from both publicly available and internal-only content from WWT's platform to achieve our vision for GenAI. This data source also includes indexed speaking transcripts from the many events hosted on wwt.com to collect valuable knowledge from our speakers and panelists.
- Advanced Technology Center (ATC) POC documents are technical assets that include in-depth test plans, test cases, test outputs, plus proprietary client and technology information that result from ATC engagements.
- ServiceNow record for POCs contains more than 4,000 records for POCs conducted in WWT's ATC. This data source functions as additional metadata detail regarding WWT's technical capabilities across different technologies and past clients, including the ability to pull project financial details and updates.
The sections below will introduce the concept of retrieval augmented generation (RAG) that enables Atom to collate information and capture value across these three data sources. In parallel, our development team is actively working on additional data source integrations and the technical foundation to expand Atom's capabilities.
"WWT Research reports provide in-depth analysis of the latest technology and industry trends, solution comparisons and expert guidance for maturing your organization's capabilities. By logging in or creating a free account you’ll gain access to other reports as well as labs, events and other valuable content."
Thanks for reading. Want to continue?
Log in or create a free account to continue viewing Part 1: Meet Atom Ai – the GPT Powering Innovation at WWT and access other valuable content.