The new capabilities are based on the Fuse™ EDA AI Agent system, recently introduced by Siemens, and incorporate new AI technology from NVIDIA to help domain-specific, long-running AI agents reason, act, and continuously validate their decisions against deterministic, physics-based EDA engines.
Siemens' Fuse EDA AI Agent system updates are designed to help the semiconductor and PCB industry move beyond simple automation and deliver reliable, verifiable results that improve result quality, time to results, tool execution reliability, and token efficiency in long-running engineering workloads. The Fuse EDA AI Agent system is now integrated into Siemens' recently launched Intelligence Center X, enabling the creation and coordination of agents within Siemens' enterprise industrial AI environment. Intelligence Center X delivers coordinated, AI-driven processes across design, manufacturing, and supply chain, enhancing the end-to-end digital twin to enable smarter execution and more reliable results.
“Our expanded collaboration with NVIDIA enhances our industry-specific industrial AI, our physically based EDA engines, and our accelerated computing to create reliable, self-verifying AI workflows,” said Amit Gupta, senior vice president and head of AI strategy for Siemens EDA, Siemens Digital Industries Software. “By enabling long-lived, autonomous EDA AI agents to continuously validate their decisions against proven engineering tools accurately and efficiently, we help customers accelerate development, improve design quality, and increase confidence in reliable engineering outcomes.”.
“Designing semiconductors and printed circuit boards (PCBs) is among the world’s most complex engineering challenges, and AI agents need reliable tools to reason, act, and verify their work,” said Timothy Costa, vice president and general manager of computational engineering at NVIDIA. “Siemens is combining its EDA software with NVIDIA’s accelerated computing, AI software, and Nemotron’s open models to create self-checking, agent-based workflows that improve design quality, accelerate deliverables, and give engineering teams greater confidence at every step of the process.”.
Enabling Reliable Self-Checking AI Agents for Semiconductor and PCB Design:
The Fuse EDA AI Agent solution now combines Siemens' engineering intelligence and reliable verification capabilities with NVIDIA's AI infrastructure technologies to execute complex semiconductor design tasks with greater speed and accuracy:
• Optimized EDA agents, built with the NVIDIA NeMo Gym open library for agent-based environments, improve the quality of results, speed, and token efficiency in semiconductor and PCB design. This provides customers with EDA design flows that become smarter over time, thanks to self-checking agents that learn from each project to automatically improve execution strategies, optimize workflows, and better leverage accumulated context.
• The secure NVIDIA OpenShell runtime environment enables enterprise-scale design teams to run autonomous agents throughout their EDA environment with enterprise-grade security, access controls, and audit logs within regulated runtime environments.
Advanced reasoning with the latest NVIDIA Nemotron and Switchyard models accelerates design by using AI agents that understand complex engineering trade-offs at the speed of AI reasoning, supporting complex engineering workflows with improved performance and token efficiency.
NVIDIA accelerated computing and CUDA-X libraries help design teams achieve approval-quality results in hours instead of days, powering both AI reasoning and EDA engines for dramatic acceleration without sacrificing accuracy.
Taken together, these capabilities enable secure and efficient token coordination among multiple agents, real-time feedback, and improved convergence in semiconductor and PCB design and verification workflows, helping customers achieve reliable engineering results.
End-to-end design automation.
Building on these capabilities, Siemens' Fuse EDA AI agent coordinates workflows throughout the semiconductor and PCB lifecycle. Domain-specific agents collaborate on synthesis, verification, implementation, and validation processes to holistically optimize outcomes.
The new offering encompasses Siemens' EDA technologies across the entire semiconductor and electronics lifecycle, from high-level synthesis with Catapult, verification with Questa One and Veloce, and custom integrated circuit (IC) design and verification with Solido, to physical implementation with Aprisa, approval verification with Calibre, and design for testing with Tessent. It also supports advanced 3D IC integration using Innovator3D and PCB design with Xpedition.
Accelerating Custom Integrated Circuit (IC) Design with Agentive AI:
Enhanced collaboration improves Siemens' Solido characterization suite with agentive AI capabilities. These agentive workflows automate library characterization by automatically generating and verifying Liberty files, running Solido Characterizer in conjunction with Solido LibSPICE, Solido Generator, and Solido Analytics. The solution delivers production-proven results for standard advanced node, memory, and custom IP cell libraries, while reducing characterization times by more than 10x and achieving a 5- to 10-fold reduction in cost per token.
These agent-based capabilities are further extended to the custom IC design workflow with the new Solido Layout Analyzer, an AI-powered, measurement-aware solution that enables visualization, exploration, and analysis of parasitic and design-dependent effects in post-design phases. Integrated with Fuse EDA AI Agent, Solido Layout Analyzer dramatically improves design quality and engineering productivity by enabling the use of natural language commands for results analysis, correction recommendations, and report generation.
Accelerating Digital Verification with Agent-Based AI
: With verification consuming up to 70% of design time and complexity, the industry is facing an unprecedented productivity crisis. Building on the recently announced Questa One Agentic Toolkit, Siemens is extending these domain-specific agentic AI workflows with NVIDIA’s Nemotron 3 Ultra reasoning model, designed for complex, long-running agents. In benchmark tests of agentic RTL against the ACE-RTL agent, Nemotron 3 Ultra leads among open models. Its reasoning and efficiency help autonomous agents evaluate engineering trade-offs while continuously validating designs against a benchmark test suite. This enables teams to identify issues earlier, accelerate verification closure, and deliver reliable results faster.
“We are at a tipping point where the complexity of AI chips, chiplets, and 3D integrated circuits has outpaced traditional verification methodologies,” said Abhi Kolpekwar, senior vice president and general manager of Digital Verification Technologies at Siemens EDA, Siemens Digital Industries Software. “Agent-based AI is the natural next step that adapts to this complexity: agents capable of coordinating multi-domain verification, reasoning through billions of test scenarios, and delivering production-quality results in timeframes that were impossible just two years ago.”.
Availability
Siemens' expanded AI-powered EDA capabilities will be available in upcoming releases of Siemens' AI-native EDA portfolio
