Siemens is expanding its partnership with Nvidia to deliver self-verifying agentic AI workflows for EDA, helping semiconductor and printed circuit board (PCB) engineering teams shift from autonomous task orchestration to more trusted, continuously validated engineering outcomes
The new capabilities expand on Siemens’ recently introduced Fuse EDA AI Agent system and introduce new Nvidia AI technology to help long-running, domain-scoped AI agents reason, act, and continuously validate decisions against deterministic, physics-based EDA engines.
Siemens’ Fuse EDA AI Agent updates can help the semiconductor and PCB industries move beyond simple automation and deliver trusted, verifiable outcomes to improve result quality, time-to-results, tool-calling reliability and token efficiency across long-running engineering workloads.
The Fuse EDA AI Agent system is integrated into Siemens’ Intelligence Centre X, supporting agent creation and orchestration in Siemens’ enterprise industrial AI environment. Intelligence Centre X provides AI-driven, coordinated processes for design, manufacturing, and supply chain, improving the comprehensive Digital Twin to support smarter execution and more trusted outcomes.
Amit Gupta, senior vice president and chief AI strategy officer, Siemens EDA, Siemens Digital Industries Software, said, “Our expanded collaboration with Nvidia enhances our domain-specific industrial AI, physics-based EDA engines and accelerated computing to create trusted, self-verifying AI workflows. By enabling autonomous and long-running 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 trusted engineering outcomes.”
Timothy Costa, vice president and general manager of computational engineering at Nvidia, said, “Semiconductor and PCB design are among the most complex engineering challenges in the world, and AI agents need trusted tools to reason, act and verify their work. Siemens is combining its EDA software with Nvidia accelerated computing, AI software and Nemotron open models to create self-verifying agentic workflows that improve design quality, speed up results and give engineering teams greater confidence in every step of the process.”
Enabling trusted self-verifying AI agents
The Fuse EDA AI Agent solution combines Siemens engineering intelligence and verification capabilities with Nvidia AI infrastructure technologies to execute complex semiconductor design tasks and improve speed and precision:
- Optimised EDA agents, developed with the Nvidia NeMo Gym open library for agentic environments, enhance the quality, speed, and token efficiency of results for semiconductor and PCB design. This provides customers with EDA design flows that get smarter over time through self-verifying agents that learn from each project to improve execution strategies, optimise workflows, and make better use of accumulated context.
- The Nvidia OpenShell secure runtime allows enterprise-scale design teams to run autonomous agents across their EDA environment with enterprise-grade security, access controls and audit trails in governed runtime environments.
- Advanced reasoning with the latest Nvidia Nemotron models and Switchyard accelerates design with AI agents that can understand complex engineering trade-offs at the speed of AI reasoning and support complex engineering workflows with improved performance and token efficiency.
- Nvidia accelerated computing and CUDA-X libraries enable design teams to achieve signoff-quality results in hours, powering AI reasoning and EDA engines for dramatic speedups without sacrificing accuracy.
These capabilities facilitate secure, token-efficient multi-agent coordination, real-time feedback and enhanced convergence across semiconductor and PCB design and verification flows, enabling customers to achieve trusted engineering outcomes.
End-to-end design automation
Expanding on these capabilities, Siemens’ Fuse EDA AI Agent orchestrates workflows throughout the semiconductor and PCB lifecycle. Domain-specific agents collaborate across synthesis, verification, implementation and validation processes to optimise holistically.
The new offering features Siemens’ EDA technologies across the full semiconductor and electronics lifecycles, including high-level synthesis with Catapult, verification with Questa One and Veloce, custom IC design and verification with Solido, physical implementation with Aprisa, signoff verification with Calibre, and design-for-test with Tessent. It also provides support for advanced 3D IC integration with Innovator3D IC and PCB design with Xpedition.
Accelerating custom IC design
The expanded collaboration improves Siemens’ Solido Characterisation Suite with agentic AI capabilities that can automate library characterisation by generating and verifying Liberty files using Solido Characteriser with Solido LibSpice, Solido Generator, and Solido Analytics.
The solution provides production-proven results for advanced-node standard cell, memory and custom IP libraries while decreasing characterisation turnaround times by more than 10x and achieving over a 5x-10x reduction in token costs.
These capabilities extend into the custom IC design flow with the new Solido Layout Analyser, an AI-powered measurement-aware solution for visualising, exploring, and analysing parasitic and layout-dependent effects in post-layout designs.
Solido Layout Analyser is integrated with Fuse EDA AI Agent to boost design quality and engineering productivity by enabling natural language and prompting with results analysis, fixing recommendations, and report generation.
Gianbattista Lo Giudice, non-volatile memory design manager, STMicroelectronics, said, “For STMicroelectronics’ non-volatile memory team, the ability to relate layout insight directly to electrical behaviour is critical. Rather than discovering layout-dependent effects late in the process, Solido Layout Analyser brings this analysis earlier into the flow, improving design confidence and helping cut down the time we spend debugging complex design blocks by weeks. We are planning to test and validate the advantages in our ongoing design activity.”
Accelerating digital verification
With verification consuming up to 70% of design time and complexity, the industry faces an unprecedented productivity crisis. Expanding on the Questa One Agentic Toolkit, Siemens is extending these domain-scoped agentic AI workflows with Nvidia’s Nemotron 3 Ultra reasoning model for complex, long-running agents.
In agentic RTL benchmarking with the ACE-RTL agent, Nemotron 3 Ultra leads among open models. Its reasoning and efficiency enable autonomous agents to evaluate engineering trade-offs while continuously validating designs against a golden test harness, helping identify issues sooner, accelerate verification closure, and deliver trusted outcomes faster.
Abhi Kolpekwar, senior vice president and general manager, Digital Verification Technologies, Siemens EDA, Siemens Digital Industries Software, said, “We’re at an inflection point where the complexity of AI chips, chiplets, and 3D ICs has outpaced traditional verification methodologies. Agentic AI is the natural path forward that scales with this complexity: agents that can orchestrate multi-domain verification, reason across billions of test scenarios, and deliver production-quality results in timeframes that were impossible just two years ago.”
