Keysight Technologies, is bringing agentic AI to its software, enabling engineers to direct AI agents to automate complex design tasks. Customers can use their large language models (LLMs) to generate and optimize designs, with Keysight simulation validating the agents’ progress. This shifts how engineering is done, as teams can evaluate significantly more options in the same development time.
More than 60% of organizations expect to deploy AI agents by 2028, yet radio frequency (RF) engineering has been slower to follow. The discipline relies on specialist expertise and uses schematics and layouts that LLMs cannot read in a consistent, deterministic way, so the process remains largely manual. Keysight Advanced Design System (ADS) 2027 addresses this by letting teams record workflows as macros their agents can learn from and convert graphical designs into code they can read. Model Context Protocol (MCP) servers connect agents to the software, guiding LLMs and agents in their interaction with ADS.
When an engineer makes a request in natural language, their agent completes the task in ADS. The MCP servers provide the agent with documented skills and tools built by Keysight that execute specific RF work consistently, reducing variability caused by AI inference models generating answers statistically. The agent then runs Keysight simulation to validate its output.
Key benefits include:
- Creates an open ecosystem for agentic workflows: The MCP servers work with AI assistants and LLMs that organizations are already using, and with tools from multiple vendors in the same workflow.
- Speeds and expands design cycles: Agents handle repetitive setup and simulation steps in ADS, so engineers can cover more scenarios and find more optimal designs while reducing time to market.
- Shares engineering knowledge: Macros recorded in ADS capture an experienced engineer’s methods for colleagues and agents to reuse across teams.
Niels Faché, Senior Vice President, 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. Over time, agents will turn prior projects into organizational intelligence, so a customer’s best work is the foundation for each new design.”
