Massachusetts Department of Transportation (MassDOT)

MassDOT integrated GitHub Copilot into its internal IT department in summer 2024, giving software developers an AI tool that suggests and completes code as they write it.

GitHub Copilot is an AI-powered coding assistant developed by GitHub and OpenAI that generates code suggestions in real time within developers' code editors. MassDOT's deputy CIO confirmed the rollout during a May 2025 presentation, describing it as one of the agency's early AI deployments within its IT department. The practice is limited to MassDOT IT staff who write software for the agency's systems.

MassDOT tested an AI framework developed with UMass Lowell that analyzes aerial photographs to automatically detect and classify crosswalks across the entire state of Massachusetts, identifying approximately 88,000 crosswalks in 2021 imagery.

The project used annotated aerial images downloaded from MassGIS to train an AI computer vision model, which was then applied to statewide images from both 2019 and 2021. The model classified crosswalks by type (continental/zebra-style, parallel lines, or solid) and location category (intersection, midblock, or driveway). The resulting model and post-processing scripts were made available to MassDOT for further analyses. Results were expected to inform maintenance and safety planning. As of the 2025 Q1 newsletter, MassDOT listed 'AI for Sidewalk Detection' as an active research initiative under a University of Massachusetts Lowell agreement.

MassDOT deployed HEKA (Highway Engineer Knowledge Assistant), an internal AI chatbot that helps highway engineers quickly find answers to questions about project rules, regulations, and design specifications. The tool went live in November 2024 and is used daily by engineers across the Highway Division.

HEKA is built on Amazon Bedrock and uses Retrieval-Augmented Generation (RAG) to respond to queries about highway project design guides, specifications, and standard operating procedures, drawing from documents stored in SharePoint. The tool was developed through the Northeastern University Burnes Center AI for Impact co-op program. In early testing, engineers observed a 78% time savings compared to manual document searches. As of May 2025, MassDOT's AI team was exploring wider adoption with the Highway business unit.