SAN JOSE, CA, June 3, 2026 – Cadence has moved its ChipStack AI Super Agent to Level-5 autonomy, giving semiconductor teams an agent that can run design and verification workflows with limited manual prompting. Introduced at Computex 2026, the system uses Cadence electronic design automation (EDA) tools, NVIDIA Nemotron models, and NVIDIA OpenShell runtime to run dynamic simulations with Cadence Xcelium Logic Simulation and Jasper Formal Verification, delivering over 40X faster RTL validation cycles.
At NVIDIA, thousands of engineers use billions of compute hours each year to run millions of design verification tests. Each engineer will use ChipStack agents to run dynamic simulations, reducing a five-week verification loop to less than a day.
“We see our customers using AI to let their expert engineers take on more ambitious silicon designs with greater speed and confidence,” said Paul Cunningham, senior vice president and general manager of the system verification group at Cadence. “With the ChipStack AI Super Agent, we’re taking the next step – moving from AI that assists engineers to autonomous virtual engineers that can implement real design and verification work, grounded in our signoff-accurate engines and running in secure, governed environments so teams can innovate faster with confidence.”
Autonomous Verification Workflows
The ChipStack AI Super Agent can execute chip design and verification workflows while engineers inspect, guide, and collaborate when needed. It works with tools such as Codex and Claude Code, giving teams visibility into autonomous activity and system decisions.
Instead of depending on prompts, the system evaluates intermediate results, selects next actions, and iterates toward closure. It works across specification understanding, RTL generation, verification planning, formal analysis, simulation, debug, and design convergence, moving engineers from task execution to outcome supervision.
Engineering Models and Runtime Controls
Cadence ties the agent’s behavior to its design and verification engines, keeping automated actions linked to computational models and signoff-accurate results. For production use, ChipStack AI Super Agent runs inside NVIDIA OpenShell runtime, a sandboxed environment with governance, policy controls, isolation, and managed access to tools, infrastructure, and design data.
“As semiconductor designs grow more complex, engineering teams need AI agents that can accelerate verification without compromising security, control or trust,” said Timothy Costa, vice president and general manager of Computational Engineering at NVIDIA. “By securing Cadence’s ChipStack AI Super Agent with NVIDIA OpenShell and powering it with Nemotron models, Cadence is bringing governed autonomy to chip design workflows – giving customers a faster, more secure path to develop and validate advanced semiconductors.”
Cadence Agent Stack
The Level-5 update follows Cadence’s acquisition of ChipStack in November 2025. Cadence launched its first ChipStack product in February 2026 and expanded the portfolio at CadenceLIVE in April with ViraStack AI Super Agent for custom and analog design, InnoStack AI Super Agent for digital implementation and signoff, and Cadence AgentStack for coordinating agentic workflows across the design stack.
Availability
The Level-5 autonomous capabilities of ChipStack AI Super Agent and the AgentStack orchestration framework are expected to be available in the second half of 2026.
Source: Cadence
About Cadence
Cadence Design Systems is a U.S.-based technology firm that develops electronic design automation (EDA) tools, hardware, and IP for designing integrated circuits and electronic systems. Formed in 1988 through the merger of SDA Systems and ECAD, the company is headquartered in San Jose, CA. Cadence provides software and solutions for designing SoCs, PCBs, and complete electronic systems used in the semiconductor, automotive, aerospace and defense, telecommunications, and consumer electronics industries. Its tools support both digital and analog design workflows. Cadence employs about 12,000 people globally.