Cadence AuraStack Cuts PCB and Chip Packaging Design Time in Half

Cadence targets PCB and packaging bottlenecks with AI agents

Cadence Design Systems has released AuraStack, an AI agent platform designed to automate the design of printed circuit boards and advanced multi-chip packaging—two critical bottlenecks in semiconductor production. The company claims the system can cut design time in half while improving quality through early multiphysics co-optimization.

According to details first reported by Forbes contributor Karl Freund, AuraStack aims to accelerate time to market by 2X and boost productivity by 15X. Nvidia is an early adopter of the platform, which is built on Cadence Allegro AI Studio and accelerated by Nvidia hardware.

How Super Agents work

Cadence calls its agentic AI platforms "Super Agents"—systems that translate design team intent into working silicon. The company has now deployed four such suites covering design and verification, analog chip design, digital chip implementation, and now PCB and advanced packaging design.

At the core of these agents are "Mental Models," knowledge graphs that aggregate design data, specifications, diagrams, libraries, and other human-readable content representing design intent. These models serve as ground truth sources that enable agents to plan, orchestrate, and monitor execution autonomously—tasks that would otherwise consume significant engineering time.

The multiphysics capabilities are particularly important for PCB and packaging work. Boards can warp, crack, or melt under intense thermal loads from modern chips. Advanced packaging technologies like TSMC's CoWoS (Chip-on-Wafer-on-Substrate) represent one of the largest supply chain bottlenecks in the AI semiconductor industry today.

Why it matters

The application of AI agents to chip design workflows represents one of the most significant advances in electronic design automation in years. These tools are enabling major chip companies like Nvidia and AMD to compress historic two-to-three-year design cycles into annual product cadences—a shift that directly accelerates the pace of AI hardware innovation. As advanced packaging capacity remains constrained, tools that reduce design iterations and improve first-pass success rates become increasingly valuable.

Availability and competition

The ChipStack AI Super Agent is now available for customer deployments. Two other Cadence AI SuperAgents—ViraStack and InnoStack—are in early engagements with development partners.

Cadence faces competition from other major EDA vendors including Synopsys and Siemens, which are also rapidly developing and deploying agentic AI capabilities to their customers.

Freund, founder and principal analyst at Cambrian-AI Research, first reported these details in Forbes. He disclosed that both Cadence and Nvidia are clients of his research firm.