Understand this story
On October 29, 2026, Siemens launched an intelligent engineering workflow capable of autonomously orchestrating 3D-IC design and analysis tasks. According to Semiconductor Industry Observer, the workflow uses the Fuse EDA AI Agent as an MCP aggregation layer to interface with Claude Code, autonomously orchestrating 3D-IC electrothermal co-design and linking seven Siemens EDA tools across nine stages, requiring 100–200 iterations and a total duration exceeding 12 hours. The report states that every decision in the workflow is verified by deterministic, physics-based EDA solver engines; a single round can cover more than 200 to 500 design points, tool configuration efficiency is improved by up to 20 times, manual workload is reduced by up to 95%, and the number of evaluable options reaches up to 50 times that of traditional manual workflows. No further progress has been disclosed at present.
AI-generated from public reports
Latest development · Report
Siemens Fuse EDA AI Agent: Using Physical Verification to Backstop Agentic EDADevelopments
1 confirmed developments
Siemens launches intelligent engineering workflow for autonomous scheduling of 3D-IC design analysis
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 29
Semiconductor Industry Observer
Siemens Fuse EDA AI Agent: Using Physical Verification to Backstop Agentic EDA
Siemens has launched an intelligent engineering workflow in which the Fuse EDA AI Agent serves as an MCP aggregation layer connecting to Claude Code, autonomously orchestrating 3D-IC electrothermal co-design, linking seven Siemens EDA tools across nine stages, requiring 100–200 iterations and a total duration exceeding 12 hours. Every decision in this workflow is verified by a deterministic, physics-based EDA solver engine; a single round can cover more than 200 to 500 design points, tool configuration efficiency is improved by up to 20x, manual workload is reduced by as much as 95%, and the number of evaluable design options reaches up to 50x that of traditional manual workflows.