TLDR: A generative AI assistant named HEKA, developed by Northeastern University graduate Sai Panindra Santosh Kumar Majji, is significantly enhancing the efficiency of MassDOT engineers. Addressing challenges like extensive documentation and a wave of retirements, HEKA provides rapid access to critical information, leading to substantial time savings and improved onboarding for new hires.
In a significant stride towards modernizing public sector operations, a generative artificial intelligence assistant, affectionately nicknamed HEKA, is transforming how engineers at the Massachusetts Department of Transportation (MassDOT) access vital information and perform their duties. Developed by Northeastern University graduate Sai Panindra Santosh Kumar Majji, HEKA stands for Highway Engineer Knowledge Assistant and is one of the pioneering AI tools rolled out by the state as part of the ‘AI for Impact’ program, a collaborative initiative between Northeastern and the Commonwealth of Massachusetts.
The genesis of HEKA stems from a critical need within MassDOT. With a wave of retirements and an ever-increasing workload, new engineers often face the daunting task of navigating an immense volume of documentation to get up to speed. Anu Goutham, Deputy Chief Information Officer at MassDOT, highlighted this challenge, stating, “The problem is there is so much documentation. Depending on where the engineer is hired into — whether it’s the bridge division, maintenance division, construction division, safety division, etc. — they’ve got to get up to speed in terms of the baseline processes and standard operating procedures, the specifications and more.” While documents had been digitized, their sheer number and the depth of information within each engineering project made an AI assistant invaluable.
Majji, a student in the first cohort of the ‘AI for Impact’ program in spring 2024, worked directly with MassDOT’s highway division to devise a more efficient onboarding solution. He developed a prototype using ChatGPT, feeding it relevant documents, and iteratively refined it based on extensive feedback from MassDOT engineers and stakeholders. Majji explained the inspiration behind the name, “Heka is also the name of the Egyptian god of knowledge — he devours all the knowledge and spreads it. So it kinda makes sense.”
HEKA’s primary function is to provide engineers with quick answers to their questions, assist in finding specific documents, and help locate correct project requirements. This capability is crucial for streamlining processes and ensuring accuracy in designing Massachusetts’ highway network. Early testing has demonstrated remarkable results, with MassDOT engineers observing a 78% time savings compared to manual information retrieval. Majji noted, “We realized that if we can use AI so that we can provide engineers answers to all their questions quickly, help them with finding documents and finding the correct project requirements and everything, that would be really helpful.”
Also Read:
- EPA Revolutionizes Document Processing with Generative AI, Achieving Significant Efficiency Gains
- California Leads Nation with AI-Powered Grid Management to Prevent Power Outages
The development culminated in several presentations to high-ranking state officials, including Massachusetts Governor Maura Healey and state Technology Secretary Jason Snyder, underscoring the state’s commitment to leveraging AI for public good. The success of HEKA exemplifies the potential of the ‘AI for Impact’ program, which places Northeastern co-op students with state agencies to develop experiential AI products aimed at improving public services and positively impacting the quality of life for millions of residents.
