The GST Council has recognised Andhra Pradesh’s use of artificial intelligence and advanced data analytics in tax administration, citing improvements in transparency, accountability and the detection of tax evasion through risk-based enforcement.
The appreciation came at the 57th meeting of the GST Council in New Delhi, presided over by Union finance minister Nirmala Sitharaman. Andhra Pradesh has deployed AI-enabled systems for statutory functions including scrutiny of returns under Section 61, audit under Section 65 and inspection under Section 67 of the GST Act.
The state’s AI-based risk assessment engine combines GSTN data, e-way bill information and third-party datasets to identify cases considered high-risk using objective, data-driven parameters. According to the Andhra Pradesh tax department, the system is intended to reduce subjectivity in selecting cases for scrutiny and enable officers to focus on cases where the risk of evasion is higher.
During the first six months of AI-enabled scrutiny, 10,817 cases were identified and tax evasion worth ₹743 crore was detected, compared with ₹366 crore under the earlier system. Average detection per case increased from ₹3.08 lakh to ₹27.63 lakh, according to the department.
The system retains human oversight. Cases can be escalated to the joint commissioner, the regional internal monitoring committee or the state internal monitoring committee where required. Statutory notices continue to be issued by designated officers, keeping formal accountability with authorised officials rather than transferring decision-making entirely to the technology.
“AI is helping us move from subjective selection to objective, risk-based enforcement. The technology enables officers to focus their efforts on high-risk cases while ensuring transparency, accountability and human oversight,” Babu Ahmad, chief commissioner of state tax, Andhra Pradesh, said. He added that the GST Council’s recognition and interest from other states reaffirmed Andhra Pradesh’s position in technology-driven tax administration.
The department has also developed an AI-powered Legal Assistant based on a knowledge base containing around 22,000 judicial pronouncements and the GST statutory framework. The tool assists officers in preparing legal instructions, paragraph-wise remarks, counter-affidavits and replies. Its outputs remain subject to approval by competent officers.
The Legal AI platform currently supports 13,719 cases. These include 8,098 matters before the First Appellate Authority, 577 appeals before the GST Appellate Tribunal and 5,044 matters before the high court. The department said the platform had improved consistency and efficiency in handling litigation without a corresponding increase in legal manpower.
The development places tax administration within a wider shift towards data-led public-sector decision-making. For Andhra Pradesh, the immediate measure of the system is the increase in detected evasion and the use of objective parameters in case selection. Its institutional safeguard is that notices and supervisory decisions remain with designated officers.
The model is also drawing attention beyond the state. Delegations from Rajasthan and Chhattisgarh have visited Andhra Pradesh to study its AI-based systems, while Assam, Delhi, Uttarakhand and other states have expressed interest in examining the initiatives. The reported interest indicates that the next phase will involve assessing whether the systems and oversight arrangements can be studied or adapted by other state tax administrations.
