Field Services Technician

Siemens adds self-verification for long-running EDA agents. Self-verifying agents can manage extended semiconductor design workflows, but deterministic EDA tools and human engineers still determine whether results are valid. Siemens recently expanded its strategic partnership with Nvidia to add new AI capabilities to the Fuse EDA AI Agent, enabling self-verifying agentic AI workflows for semiconductor and printed-circuit board (PCB) design. The goal is to move toward agents that can remain active throughout long-running semiconductor and PCB design workflows. Partner Content The new capability combines Siemens' electronic design automation (EDA) software with Nvidia's AI open models, agent software, secure runtime, and accelerated computing stack. It also spans Siemens' EDA technologies, including Catapult high-level synthesis, custom IC design and verification with Solido, Aprisa physical implementation, Calibre signoff verification, and Tessen design-for-test. The Fuse EDA AI Agent system, now integrated into Siemens' recently launched Intelligence Center X, supports agent creation and orchestration in its enterprise industrial AI environment. The self-verifying AI workflows enable autonomous and long-running EDA AI agents to continuously validate their decisions against proven engineering tools. It allows the agent to monitor a workflow, inspect the results, change its configuration, and run other operations while checking its progress against established EDA engines. This is what Siemens calls self-verification. The language model does not, by itself, determine whether a design is correct. Instead, the agent uses simulation, verification, and physical design tools to produce the engineering evidence for the next decision. For example, library characterization using Siemens' Solido Characterization Suite with agentic AI can reduce characterization turnaround by more than 10x and token cost by 5x to 10x, according to the company. These agentic workflows automatically generate and verify Liberty files via Solido Characterizer with Solido LibSPICE, Solido Generator, and Solido Analytics. The journey toward self-verifying agents. At DAC 2025, Siemens introduced the Fuse EDA AI System, which provided the data and model infrastructure to use generative AI with EDA data. The Fuse EDA AI Agent, announced at Nvidia GTC in March 2026, added an execution layer. The supervisory agent can break an engineering objective into tasks, delegate work to specialized agents, and connect to EDA applications through Model Context Protocol (MCP) interfaces. This new expansion, released at DAC 2026, adds long-running agents that can keep working after the first tool call. For example, an agent can launch a simulation, inspect the returned logs, identify a failure, modify the setup, and try again. The Fuse EDA AI Agent translates an engineer's objective into a plan and the specialized agents select tools and execute the steps. Extending the agentic AI workflows with Nvidia's Nemotron 3 Ultra model provides reasoning for planning and multi-step execution, while the Nvidia NeMo Gym open library is used to evaluate agent behavior to improve results and optimize workflows. It also leverages Nvidia OpenShell secure runtime to provide a secure environment for running the agents. But the engineering result comes from Siemens' EDA tools. For instance, a model may decide which SPICE analysis to run or if another process, voltage, and temperature (PVT) corner is needed, but the simulator produces the electrical result. "The goal is not to replace physics with AI," said Timothy Costa, general manager for industrial and computational engineering at Nvidia. The objective is to connect AI reasoning with accelerated simulation and physics-aware models and keep trusted engineering tools as the source of validation, he added. How a long-running agent handles library characterization. Library characterization shows why this type of agent can be useful even when the underlying simulations are already automated. In the case of a standard-cell, memory, or custom-IP library, it has to be characterized across different operating conditions before its timing and power models can be used. Engineers first configure the library and run preliminary simulations to confirm that the environment is working correctly. Amit Gupta, senior vice president and general manager of Solido Custom IC and chief AI strategy officer, at Siemens EDA, Siemens Digital Industries Software, described this process as "pipe cleaning." If simulations fail because of an incorrect setup or convergence issue, an engineer has to inspect the result, change the configuration, and rerun the task. Once the setup is stable, the full characterization run begins. Engineers continue to monitor failures, review outliers, and decide if additional PVT corners need to be simulated before the Liberty models can pass quality checks. "It comes out to about a four-to-six-week process for a library," Gupta said. The Solido Characterization agent automates much of this supervisory loop. Gupta said an engineer can initiate the process with a single prompt. The agent can launch hours-long runs, monitor them, react to failures, change configurations, rerun jobs, and perform final quality assurance steps. The workflow combines Solido Characterizer, Solido LibSPICE, Solido Generator, and Solido Analytics. Characterizer manages the characterization tasks, LibSPICE runs the circuit simulations, Generator produces the Liberty models, and Analytics examines the results and supports outlier analysis. The productivity gain comes from reducing the manual work between simulations. Nvidia CUDA-X libraries can also accelerate numerical operations used by the simulation and physical verification tools to reduce the time between an agent's action and the feedback it needs for the next decision. Nvidia's PhysicsNeMo open-source PyTorch framework for physics AI models provides another layer where physics-aware models can give the agent fast estimates to explore a design and decide where a higher-fidelity simulation is required. But Costa said those models are not a substitute for engineering validation. According to him, trusted solvers, test data, and domain-specific criteria are the final references. Cross-domain autonomy remains the larger engineering challenge. The Solido characterization example is a workflow with well-defined inputs, tools, and acceptance checks. Extending the same autonomy across several EDA domains is more difficult. Gupta said Siemens is currently focused on long-running agents within individual areas such as custom IC design, digital verification, design-for-test, and Calibre physical verification. "What we see as the next step is being able to stitch those product families together," he added. Siemens has demonstrated an early example, where Calibre detects a design rule violation, and the agent invokes Aprisa semiconductor software for a digital physical design repair or Solido for an analog repair. This moves the agent from identifying a problem to changing the design, and it also creates new verification requirements. Fixing a local design rule check violation can create a timing, congestion, or signal integrity problem somewhere else in the design. The challenge is more than exposing additional applications through MCP. Even a cross-domain agent has to understand how different representations of the same design correlate to one another. Gupta explained that Siemens is developing EDA ontologies that map relationships between different domains and improve the models' ability to understand the different data types. This context is necessary because a change in one stage may invalidate results elsewhere. Human judgment remains part of the design and verification workflow. When an agent repairs a design rule violation, it can create another physical problem, he added. Engineers therefore need to observe the agent's actions, pause or stop execution, and redirect the workflow. Near-term deployment of this capability will remain domain-scoped and supervised. But more full-scale autonomy comes when EDA companies can preserve engineering intent, while agents can move across multiple tools, data models, and verification steps. This shows that agentic EDA is not replacing the physics-based tools used to design and verify chips. The agent can keep the workflow moving and decide what should happen next, while the deterministic EDA engines and human engineers determine if the results can be trusted. The expanded EDA AI capabilities will be available in upcoming releases of Siemens' AI-native EDA portfolio. VIRTUAL events. Industry summits * | Electronica Forums 2026 * | Arrow New Space Technology Summit 2026 * | Autonomous Agriculture Technology Summit 2027 EXPERT-LED webinars. ON DEMAND or Live * | Edge-first Architectures for Building and Campus Safety - EE Times * | Lower Risk, Save Costs with Certified WiFi & BLE Modules - EE Times * | Power Distribution Systems Electrification Evolution - EE Times Featured WHITE PAPERS. Technical Resources * | Loop Compensation and Decoupling Design with "The Loop Compensator" - EE Times * | Selecting the Correct Level of DC-DC Converter for Your Application - EE Times * | The Future of Open Cable Systems: Conditional Access Migrates to DCAS - EE Times

Pack Expo 2026 live: Siemens showcases AI-powered digital twin for flexible filling. Key takeaways. * Siemens is showcasing an AI-powered digital twin developed with PepsiCo and Nvidia to simulate and optimize packaging and filling. * The system supports flexible production by adapting filling parameters, and pallet configurations. * Siemens says connected facility data can improve traceability and help brands respond to growing EPR reporting requirements, while human operators retain oversight of AI-generated decisions. Siemens is presenting its digital twin robotic solution, made in collaboration with PepsiCo and Nvidia, that uses AI to improve the speed and efficiency of packaging and bottling lines, at the ongoing Pack Expo International 2026 exhibition in Chicago, US (Oct 18-21). The partnership combines Siemens' digital twin and industrial AI technologies with Nvidia's AI and visualization capabilities to create high-fidelity virtual models of PepsiCo's manufacturing and warehouse operations. On the show floor, Packaging Insights, speaks with Andrea Sassetti, digital enterprise innovation manager at Siemens, about how the solution helps brands respond to emerging beverage trends and growing US EPR pressures. "The solution is a full representation of a comprehensive digital twin. But behind the scenes, there are multiple software programs that are running that allow us to simulate what is happening for the packaging, filling, and robot. All of that is merging into the full facility." Across the US, EPR legislation is booming, as multiple states are enacting, or are in the process of enacting, the producer pays principle. Sassetti explains Siemens' digitally integrated solution offers "trustability" by helping brands meet the data requirements set out in EPR's. "We are able to collect all the different information that is happening behind the scenes of the entire facility. All the data is connected, and we can provide trustworthiness." "We are also partnered with a couple of companies that are able to collect all the information and provide a certification of the authenticity of the entire system." Filling flexibility. Siemens aims to digitally transform the filling capabilities of PepsiCo using physics-based digital twins and AI, with the Digital Twin Composer as a cornerstone solution. Siemens' AI-powered digital twin helps PepsiCo simulate and optimize filling, packaging, and palletizing operations.Sassetti says that the system can choose liquid and powder specifications and then fill the bottle or can accordingly. "From the palletizer point of view, we are able to make multiple layers, each one with a different package, so that brands can deliver what is needed for customization." He outlines that PepsiCo doesn't always need a largepallet of one flavor, but that a mix of colors and flavors tailored to a specific event or distribution pathway are sometime preferable. The solution enables PepsiCo to "simulate all the details" for accurate and flexible filling. Sassetti explains that the system also allows product testing and validation to ensure quality. He adds that the system could be adaptable to many markets, such as wearable devices, but asserts that "the technology can also be applied with a more traditional fixed line." Also at Pack Expo 2026, Siemens has unveiled its next-generation Sinamics drives solutions, a range of motor drives designed to improve connectivity, standardization, and control across packaging and production equipment. "Targeting standard industrial applications, from pumps, fans, and conveyors to processing machinery, the solutions expand the drives portfolio for industrial applications with a modern, general-purpose drive," says the company. Adaptable supply chains. Sassetti explains how the filling system taps into demand for localized supply offerings, especially for big events like the FIFA World Cup or the Rio Carnival in Brazil. "It's what we call a pop-up factory," he notes. "It's a temporary factory like a pop-up shop, but instead of selling, we are making the product. Usually, brands need to ship products." He underscores that a localized filling facility is especially important for brands adapting to fast-changing market trends. "It's difficult to estimate what the trend will be or who's going to come and visit, and brands need to adjust the flavor. We created this factory with PepsiCo that can receive the order faster and then use AI to think about what the next trend will be." Andrea Sassetti, digital enterprise innovation manager at Siemens.He adds that AI software integrated into the system can help PepsiCo predict trends based on things like weather, population demographics, season, or the number of spectators at sporting events. "Plants are becoming adaptive so that they can react faster. Traditionally, brands need to add a code into the recipe, with time and speed [requirements]." "But in this case, there's an AI model that is running directly to the equipment that can determine, based on the viscosity, based on the particle size of the material, what will be the best combination of set point to mix [the beverage]." AI caution. Sassetti tells Packaginginsights that, while the simulation uses AI "as much as possible," there is always a supervisor to take corrective action in case there are issues. "It's just like when you're opening Gemini, and it says: be careful, this is code, it's AI-generated, and you copy and paste at your own risk," he remarks. "We have the same things here in that we can give you a possible solution, but the operator needs to have full confirmation of that." Earlier this year, Packaging Insights spoke to Jude Pullen about his collaboration with product and service solutions provider RS Group and Nvidia to enhance efficiency in packaging production. With live reporting from Milana Nikolova at Pack Expo 2026.