The GST Council has praised Andhra Pradesh’s use of artificial intelligence and advanced data analytics in tax administration after the state detected tax evasion worth ₹743 crore through AI-enabled scrutiny in the first six months of implementation.
The recognition came at the 57th meeting of the GST Council in New Delhi, presided over by Union finance minister Nirmala Sitharaman. The council said Andhra Pradesh’s systems had improved transparency, reduced subjectivity in selecting cases, strengthened accountability and supported risk-based enforcement.
Andhra Pradesh has introduced AI-enabled systems for key statutory functions under the GST Act, including scrutiny of returns under Section 61, audits under Section 65 and inspections under Section 67. Its risk assessment engine combines GSTN data, e-way bill information and third-party datasets to identify cases considered high-risk using data-based parameters.
According to the state tax department, the system identified 10,817 cases during its first six months. Tax evasion detected through these cases totalled ₹743 crore, compared with ₹366 crore under the earlier system. Average detection per case increased from ₹3.08 lakh to ₹27.63 lakh.
The department said the technology operates with supervisory safeguards and does not remove human responsibility from enforcement. Cases can be escalated to the joint commissioner, the regional internal monitoring committee or the state internal monitoring committee when required. Statutory notices continue to be issued by designated officers.
“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 council’s recognition and interest from other states reaffirmed Andhra Pradesh’s position in technology-driven tax administration.
The state 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 with 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: 8,098 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 systems are also drawing interest from other states. Delegations from Rajasthan and Chhattisgarh have visited Andhra Pradesh to study its AI-based tax administration, while Assam, Delhi, Uttarakhand and other states have expressed interest in examining the initiatives.
