CAG develops sovereign LLM platform to detect procurement risks and improve public audits

The Comptroller and Auditor General (CAG) is developing a large language model (LLM) platform and deploying artificial intelligence (AI) and machine learning (ML) tools to strengthen public sector auditing, improve risk detection and enable faster identification of procurement concentration and cartel-risk indicators, PTI reported.Comptroller and Auditor General K Sanjay Murthy on Wednesday said the country’s apex auditor is modernising audit systems to improve the quality, speed and analytical depth of public auditing.“Our modernised audit systems will identify repeated bid rotations, suspicious clustering of vendors, abnormal pricing similarities, concentration of awards, and patterns of limited competition across tenders, faster and more efficiently,” Murthy said at an event in the national capital.Speaking as the chief guest at the 17th Annual Day of the Competition Commission of India (CCI), Murthy said the CAG’s procurement audits across major sectors have evolved from reporting isolated irregularities to identifying larger systemic patterns.The auditor is using AI and ML tools to analyse entire datasets rather than relying on sample-based reviews.According to Murthy, the CAG processes nearly 20,000-25,000 inspection reports every year, containing lakhs of audit observations linked to government expenditure, infrastructure projects, taxation and procurement.Going forward, Murthy said the vision is to enable near real-time identification of procurement concentration and cartel-risk indicators.“Future audit analysis may eventually generate dynamic competition-risk heatmaps across sectors, geographies, contractor ecosystems,” he said.He also said the CAG LLM is being developed as a sovereign artificial intelligence platform for public sector auditing and institutional knowledge management.“These LLM platforms are expected to significantly improve the quality, speed, and analytical depth of public auditing by assisting officers in identifying risk areas, designing audit plans, detecting systemic vulnerabilities, and enabling faster sharing of institutional knowledge and best practices across various stakeholders,” Murthy noted.With enhanced technological capabilities, the CAG also plans to strengthen analysis of GST systems, FASTag and logistics datasets, mining dispatch systems, power exchanges, transport networks and public procurement repositories.