On 5 November 2025, confronted with the most consequential regulatory question of the decade, the Government of India declined to pass a law. In place of a statute, the Ministry of Electronics and Information Technology released the India AI Governance Guidelines under the IndiaAI Mission ~ a framework built not around prohibitions and penalties but around seven sutras, a term lifted from classical Indian grammarians rather than from Brussels or Washington. The vocabulary was not ornamental. It was the argument. The first thing to grasp is what the Guidelines are not.

They are not legislation. They create no new offence, impose no fine, and confer no fresh statutory power. Their drafting committee said as much in terms: a separate AI-specific legislation, it concluded, “is not required at this stage, as most risks can be addressed through current laws and timely enforcement.” Those current laws are not thin ~ the Information Technology Act of 2000, the Digital Personal Data Protection Act of 2023, the Copyright Act, consumer and criminal statutes ~ and the Guidelines lean on them deliberately, reserving fresh law for the gaps that existing law cannot reach. The document has four moving parts.

Seven guiding principles, styled sutras, sit at the top. Beneath them run recommendations across six pillars of governance; then an action plan mapped to short-, medium- and long-term horizons; and finally practical guidance for developers, deployers and regulators. The seven sutras are worth naming precisely because secondary summaries routinely blur them: Trust is the Foundation; People First; Innovation over Restraint; Fairness and Equity; Accountability; Understandable by Design; and Safety, Resilience and Sustainability.

Note the sixth. It is not “transparency,” the word most commentators reach for, but “Understandable by Design” ~ a subtler and more demanding idea.........

© The Statesman