Officials working with NHAI projects will now be able to identify defects in highways and get swift answers on ways to rectify them — all with the click of a mouse.In a move to check deficiencies in Detailed Project Reports (DPRs) of new highways, get faster analysis on road defects, identify faulty signages and to synthesise learnings from previous arbitration and project delays, the National Highway Authority of India (NHAI) has developed its own AI system. The system, deployed recently, works on the basis of NHAI’s voluminous repository of documents such as circulars, act, Indian Roads Congress (IRC) codes and monthly reports.It acts as an assistance tool by reducing the burden to go through multiple circulars, SOPs (Standard Operating Procedures) or IRC codes, which run into hundreds of pages, said officials.As of now, only NHAI officials have been given access to this system.NHAI Chairman Santosh Kumar Yadav said that the access will also be granted to consultants and contractors soon after ensuring that there are no loopholes that could lead to misuse of the Authority’s information.“This system was needed because when we carried out the workflow study of Project Directors and regional officers of NHAI last year, we found that they have to be unnecessarily involved in a number of work, which can be easily done through AI tools. With this system in place, any official can check the defect of a highway by just uploading a photo. The system will quickly run through hundreds of guidelines, codes, notification, specifications and give the result,” said Yadav.He said that NHAI’s AI system also addresses the problem of faulty DPRs, which become the foundation of any highways project. This problem has been repeatedly flagged by Union Minister of Road Transport and Highways (MoRTH) Nitin Gadkari who said that road accidents and fatalities in India are increasing because of poor civil engineers, consultants, concessionaires and substandard DPRs.Story continues below this ad“Our biggest problem is DPRs. For instance, In a Rs 2,000 crore project, there will always be a variation of Rs 200-300 crore. Besides, additional work has to be taken up. Now, we have to just upload the DPR of any project and the AI system will find the errors against IRC codes, MoRTH and standard policy circulars. Thus, these problems can be fixed in advance,” said Yadav.The NHAI’s AI team has also developed a Technical Schedule Analyzer tool, which reviews DPR’s schedule B and C documents and flags findings by severity and scoring completeness. Schedule B and Schedule C are core technical annexures that define the exact physical scope of the highway project.Apart from this, NHAI also has an in-house chat-based AI agent, Margsarthi, where officials can place their queries. For instance, a field engineer can photograph a problem-hit site and ask Margsarthi what to do next as per the guidelines. The AI tool, connected to NHAI’s datalake, went live on April 18. It has received over 50,000 queries from around 1,100 users so far. Over 40% of the questions were on circulars and documents.“When we started working on this, we found that across the organisation, the officials used to keep personal folders of circulars, Acts and similar reference material on their own computers. Even for experienced officers, it was difficult to keep track of the sheer volume of rules and regulations in force. With this system, they can get it in just one query,” said a senior engineer of the project.Story continues below this adThe other tools are Kick-Off and MPR insights, which track every issues raised in kick off meetings and monthly project reports, flags critical issues and bottlenecks with a direct link back to the original minutes, and surfaces high-priority and overdue issues, each with a recommended action and a citation to the source page.