Companies from tech giants to emerging startups are racing to build custom chips. Google has developed its own Tensor Processing Units (TPUs) optimised for AI workloads, Nvidia has partnered with Groq on specialised AI inference chips, and UK startups Fractile and Olix are building custom processors - all in pursuit of more powerful, application-tailored silicon that can handle tomorrow’s computational demands more efficiently.

Tattvam AI is introducing a novel approach to chip design by building an AI system that deeply understands circuit structure and autonomously solves complex design tasks, reducing chip development cycles.

“Chip design is fundamentally a reasoning problem over an enormous search space, not unlike the kind of reasoning that’s needed to solve hard problems in mathematics. Current AI tools, even the most advanced LLMs, struggle with the deep structural understanding that chip design demands. We’re building a reasoning model that actually understands circuits from first principles - the constraints, the tradeoffs, the interdependencies - the same way a world-class engineer would, and doing it in a fraction of the time,” said IIT-Madras alumnus Bragadeesh Suresh Babu, CEO and co-founder, Tattvam AI.

By automating key parts of the design process, Tattvam AI aims to make custom silicon accessible to more companies.