Seeking to reduce costly mistakes during highway construction, the National Highways Authority of India (NHAI) is relying on an in-house artificial intelligence (AI) tool to detect discrepancies in detailed project reports (DPRs), verify conditions on the ground and flag potential issues before they escalate into delays or cost overruns.
DPRs act as a blueprint for highway projects, determining what will be built, how it will be done, and the estimated cost.
“Detailed project reporting is our biggest problem. In A $2000 crore project, various forms $200 Crores $Rs 300 crore could arise simply because something was lost during planning. This tool helps in identifying those gaps at the DPR stage itself, said Santosh Kumar Yadav, Chairman, NHAI.
The software, called Technical Schedule Analyzer, compares information in project reports with technical standards, policy provisions, and a growing repository of field data. At present, he analyzes Schedule B and Schedule C sections of DPRs, checking project quantities and specifications against Indian Road Congress (IRC) codes, Ministry of Road Transport and Highways standards and NHAI standards, pointing out discrepancies and omissions before commencing work.
Read also:NHAI identifies land required for two flyovers at Rajiv Chowk
“Soon, the system will also derive data from drone surveys, network survey vehicle logs, geospatial information, monthly progress reports and site images to check whether what has been planned on paper matches the conditions on the ground,” a member of NHAI’s AI cell said.
Such capabilities can help identify mismatches between project designs and site reality very early in the project cycle, reducing the need for costly changes after construction begins, officials said.
The Technical Schedule Analyzer is among a growing range of AI applications being developed by NHAI’s in-house AI cell, which was established in August 2025.
This initiative emerged from an internal evaluation that found that project managers and regional staff were spending a significant amount of time dealing with routine administrative issues, contractual disputes and document review rather than focusing on site inspections and project monitoring.
To address this problem, NHAI has assembled a multi-disciplinary team comprising civil engineers, AI engineers and design professionals, including young recruits from leading institutes and the private sector. Over the course of several months, the team digitized and organized thousands of circulars, technical manuals, policy documents and engineering standards into an organized knowledge repository.
The effort has since evolved into a broader AI ecosystem centered around Margsarthi, NHAI’s in-house AI assistant who is exclusively trained on NHAI publications, codes, IRC codes and other approved technical documents. Unlike public AI platforms that draw information from the Internet, Margsarthi operates within a closed environment and relies only on vetted institutional records, project databases, and technical standards.
Launched in April, the chatbot has already handled over 50,000 queries from around 1,100 users across the organisation, according to NHAI. Officials said that each response issued by the system is linked to source documents, allowing users to verify the basis of the recommendations.
The system is currently available to NHAI officials across the country and is expected to be expanded to include freelance engineers and engineers associated with highway projects.
One of its most widely used functions is resolving technical disputes on project sites. Instead of manually searching through hundreds of pages of codes and generalizations, engineers can query the system and get an answer supported by the relevant clause.
“Many disputes arise because the contractor and the authority engineer interpret a provision differently. Earlier, both sides would spend hours reviewing manuals and circulars. Now they can bring up the issue to Margsarthi, who directs them to the relevant IRC rule or policy provision. Once everyone is looking at the same rule, disagreements are resolved much faster,” Yadav said.
The platform is also used to analyze lengthy legal and arbitration records. Tasks that previously required administrators to review hundreds of pages can now be completed in minutes, helping administrators identify key issues and prepare responses more quickly.
Another application that provides geometric guidance from field images. He gave a recent example,
Yadav said he uploaded a photo of an incorrectly cut ramp while travelling, and the system immediately identified the deficiency and suggested corrective action based on established standards.
NHAI is also developing artificial intelligence tools capable of continuously scanning project data and automatically alerting officials of delays, quality deficiencies and emerging risks. Future applications in development include automated road defect analysis, maintenance planning, AI-assisted drawing reviews, signage planning, and support for environmental and deforestation applications.
However, officials emphasized that the tools are intended to aid decision-making, not replace it. While engineers and project managers are encouraged to use AI-generated insights, responsibility and accountability for project decisions will still rest with the relevant officials.
