Keysight Technologies (NYSE: KEYS) has added agentic AI capabilities to its design software, allowing engineers to use large language models (LLMs) to automate radio frequency (RF) circuit generation, verification, and optimization tasks.

The new features, available in Advanced Design System (ADS) 2027 and RF Circuit Simulation Professional, use Model Context Protocol (MCP) servers to connect AI agents to Keysight's simulation tools. Engineers can issue requests in natural language, and the connected agent completes the corresponding task within ADS, with Keysight's simulation software validating the output.

The release also includes macro recording, which captures engineering workflows that agents can learn from, and a feature that converts graphical designs into code that LLMs can process. Python script generation is also included in the update.

Niels Faché, Senior Vice President of Keysight Design Engineering Software, said: "Agentic engineering is reshaping every stage of design from concept through verification. Our decades of simulation and domain expertise validate AI results before they reach hardware."

According to a Gartner report cited in the company's press release, more than 60% of organizations expect to deploy AI agents by 2028. Keysight noted that RF engineering has been slower to adopt such tools due to its reliance on specialist expertise and design formats that LLMs have difficulty reading consistently.

The MCP servers are designed to work with AI assistants and LLMs that organizations are already using, as well as tools from multiple vendors within the same workflow.