en.Wedoany.com Reported - At Computex 2026, Cadence introduced the industry's first fully autonomous virtual agent AI design engineer, expanding the ChipStack AI super-agent to Level 5 autonomy. Based on Cadence's AI-driven electronic design automation (EDA) portfolio (powered by NVIDIA's Nemotron model) and secured by the NVIDIA OpenShell runtime, this product enables customers to run dynamic simulations within automated workflows. At NVIDIA, thousands of engineers use billions of compute hours annually to run millions of tests for design verification. Each engineer can leverage the ChipStack agent to run hundreds of dynamic simulations via Cadence Xcelium logic simulation and Jasper formal verification, accelerating RTL verification by over 40 times, compressing a typical five-week verification cycle to less than a day, significantly speeding up the verification process for complex semiconductor designs.
The ChipStack AI super-agent now operates at Level 5 autonomy, independently executing complex chip design and verification workflows while allowing engineers to inspect, guide, and collaborate on demand. Instead of relying on step-by-step prompts, the system evaluates intermediate results, determines next actions, and iterates on tasks until completion, covering specification understanding, RTL generation, verification planning, formal analysis, simulation, debugging, and design convergence. Natively integrated with collaborative environments and compatible with tools like Codex or Claude Code, it provides transparency into autonomous activities, helping teams track system progress and decisions. This shifts engineers from executing individual tasks to overseeing outcomes and guiding intent, with autonomous verification workflows reducing traditional multi-week verification cycles to under a day in cutting-edge deployments.
The autonomous agent's behavior is tightly coupled with Cadence's physics-based core design and verification engines, ensuring AI-driven actions are grounded in validated computational models and signoff-accurate results, building trust for high-stakes engineering projects. To support production deployment, the ChipStack AI super-agent runs within the NVIDIA OpenShell runtime, a sandbox environment that enforces governance and helps protect sensitive IP through policy control, isolation, and managed access to tools, infrastructure, and design data. Cadence's physics-based engines and OpenShell's security architecture together provide a practical path from supervised pilots to production-level autonomous workflows.
Cadence continues to advance in agent AI with NVIDIA's support. Following the acquisition of ChipStack in November 2025, the company launched its first product in February 2026, expanded its AI super-agent portfolio at CadenceLIVE in April, introducing the ViraStack AI super-agent for custom and analog design, the InnoStack AI super-agent for digital implementation and signoff, and the Cadence AgentStack orchestration framework for coordinating agent workflows across the design stack. Cadence is now extending these capabilities to full autonomy.
The Level 5 autonomous capabilities of the ChipStack AI super-agent and the AgentStack orchestration framework are expected to be available to early customers in the second half of 2026.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
