Cadence is building an autonomous register-transfer level (RTL) engineer with NVIDIA NemoClaw that orchestrates Cadence Design Systems ChipStack for design and verification. This workflow is cutting time for RTL verification—a critical step in digital circuit design—from weeks to hours.
Autonomous Agents Orchestrate Complex Engineering Workflows
NVIDIA NemoClaw provides an open blueprint for building specialized, long-running agents with a secure runtime and frontier models. The architecture includes a choice of harness to integrate with existing enterprise orchestration frameworks like OpenClaw and Hermes, alongside a model router and NVIDIA NeMo libraries for customization. At its core, the NVIDIA OpenShell open-source runtime governs how agents access files, networks, and tools, enforcing policy-based security at the layer where agents interact with industrial environments.
Major industrial software providers are leveraging this blueprint to automate the end-to-end simulation and design lifecycle. Cadence is focusing on digital circuit design, while Siemens is integrating NemoClaw into the Fuse EDA AI Agent to plan and orchestrate domain-scoped multi-tool workflows for semiconductor and printed circuit board system design. Dassault Systèmes is productizing the 3DEXPERIENCE Agentic Platform to run autonomous agents for design, simulation, and manufacturing in a secured environment.
Startups and Specialized Agents Drive Design Optimization
Beyond established software leaders, startups are using NemoClaw to compress design iteration cycles. Flexcompute is applying the technology to multiphysics co-packaged optics design, using autonomous workflows to explore thousands of design variants overnight. Luminary is building a long-running AI engineer to reduce the complexity of training AI physics models by autonomously orchestrating data generation, machine learning model selection, and training loops.
Other specialized applications include nTop, which uses NemoClaw to compress days of geometry iteration into hours for aircraft design, and PhysicsX, which is partnering with the Microsoft Surface team to automate the full thermal simulation lifecycle for consumer electronics. These agents move beyond simple automation, performing tasks like mesh sensitivity analysis, simulation data generation, and continuous accuracy monitoring across the design exploration process.
These autonomous AI engineers represent a shift from manual, multi-week engineering processes to automated, AI-driven design cycles that enable rapid, large-scale optimization of complex industrial systems.
Source: Industrial Software Leaders Build Secure, Autonomous AI Engineers With NVIDIA NemoClaw
Domain: blogs.nvidia.com
Comments load interactively on the live page.