Engineer Builds AI Agent to Master Software, Saving Hundreds of Hours and Hinting at the Future of Infrastructure Design

An innovative application of generative AI, unveiled at the 2025 Bentley Illuminate conference, is poised to reshape how engineering firms train and deploy their talent.

Kyle Rosenmeyer, a model-based design leader at VHB, has built a custom AI agent using Microsoft’s Copilot Studio that rapidly teaches engineers how to use complex Bentley software, effectively eliminating the need for engineers to spend time “learning CAD.”

Rosenmeyer’s AI agent acts as an instant software tutor and troubleshooter, allowing engineers to ask natural language questions about Bentley products like OpenRoads or ProjectWise and receive precise, step-by-step answers.

He claims the tool has saved him over 100 hours in the past year and, based on a company survey, saves other users an estimated one to two hours per week.

“Engineers aren’t paid to learn software. They’re paid to design roads and bridges,” Rosenmeyer said. His central philosophy is that software should “get out of the way” so engineers can focus on core design tasks.

The custom agent was built on Microsoft’s low-code Copilot Studio, a platform designed for creating internal AI assistants.

Rosenmeyer attributes the agent’s high performance to a meticulously crafted “system prompt” that defines the AI’s personality and expertise, combined with access to five distinct knowledge sources: Bentley’s main site, blog, official documentation, YouTube channel, and, most critically, the user-generated content from the Communities forums.

“User-generated content… is where real engineers are asking real questions and sharing real insights. It’s messy but gold,” Rosenmeyer noted, emphasizing that the AI’s ability to “reason” its way to solutions for vague questions is a testament to the quality and accessibility of Bentley’s deep, well-structured public documentation.

The VHB agent is currently deployed within Microsoft Teams, making it instantly accessible and secure for all employees. Rosenmeyer stressed that building such a tool is “stupid easy,” requiring only basic skills to input the system prompt and relevant URLs.

He is now leading workshops to share the blueprint with others, advocating for a widespread adoption of similar Copilots across the industry.

Looking ahead five years, Rosenmeyer envisions the entire learning curve for professional software disappearing. “You won’t ‘learn CAD.’ You’ll just talk to your assistant,” he predicted.

Furthermore, he argues this shift in the design office is critical preparation for a larger transformation: the rise of “Physical AI” and robotics on construction sites. As autonomous equipment becomes a reality, the engineering and design workflows must be fully digitized and integrated with AI tools to manage the infrastructure data layer, ensuring the industry is not “caught unprepared” for the coming automation wave.

- Video Advertisement -

Related Post

China Uses Digital Twin  to Build First Large-scale Power Station in Karst Geology

Shanghai Investigation, Design & Research Institute Co., Ltd. (SIDRI) has used Bentley’s digital engineering and digital twin technologies to overcome complex geological challenges at the Caiziba Pumped-Storage Power Station in Fengjie County, Chongqing, China. The project is the first large-scale pumped-storage power station built in an area with complex karst geology, where caves, fissures, underground […]

Viscan Transforms B29 Highway Project With Digital Twin Technology

Viscan GmbH has transformed its reality capture workflow for the B29 highway expansion in Baden-Württemberg, turning an initially unreliable digital process into a high-performance digital twin system for one of Germany’s first fully digital construction sites. The B29 project includes nine new structures, bridges, and retaining walls. Viscan’s role was to provide construction teams and […]

AI Could Predict Infrastructure Failures Weeks in Advance

AI-powered analytics are helping infrastructure engineers move from reacting to failures toward predicting problems before they become emergencies, according to Vahid Abdollahi, an Applied AI Scientist at Bentley Systems. Traditional monitoring often alerts operators only after a measurement crosses a fixed threshold. AI, however, can analyze data from multiple sensors to identify unusual patterns and […]

Bentley iTwin Capture Helps Transform City-Scale Digital Twin Development Across India

Almondz Global Infra-consultants Limited is helping transform city-scale digital twin development across India through the Government of Gujarat’s Project NAKSHA. Using Bentley’s iTwin Capture, the company created highly accurate digital twins by processing more than 100 terabytes of drone, LiDAR, and geospatial data, including over 500,000 images. The project supports smarter urban planning, disaster management, […]

Bentley Systems Expands Carbon Analysis Tools for Infrastructure Projects

Bentley Systems is highlighting its carbon analysis software as a tool to help infrastructure organizations reduce emissions, improve project efficiency, and comply with increasingly strict environmental regulations. The software, available through Bentley Infrastructure Cloud, is designed to help engineers and project teams assess the carbon impact of infrastructure projects from the earliest stages of planning […]

Bentley Systems Highlights AI-Powered Digital Twins to Improve Infrastructure Data Management

At the Cesium Developer Conference, Bentley Systems showcased how its Cesium platform, iTwin technology, and new AI tools can help solve a major infrastructure challenge: keeping project data connected throughout an asset’s entire lifecycle. Industry experts noted that valuable information created during design is often lost when projects move from planning to construction and maintenance. […]