"Vibe-code" Your Materials Testing Machine: AI-Native Configuration and Automation with MCP
"Vibe-code" Your Materials Testing Machine: AI-Native Configuration and Automation with MCP
Tuesday, September 29, 2026: 1:00 PM
308B (Québec City Convention Centre)
Materials testing machines have traditionally required specialized software development, firmware customization, and fragmented configuration workflows. As artificial intelligence matures, a new paradigm is emerging: language-driven engineering for industrial systems.
This session introduces the concept of "vibe-coding" in materials testing - an AI-native approach where engineers define test sequences, operational logic, reporting structures, and machine behaviors through structured natural language. Using the Model Context Protocol (MCP), AI systems interact with machine controllers and datasets within clearly bounded operational contexts, enabling safe and traceable configuration of automation workflows.
Rather than replacing deterministic real-time control, this architecture separates critical control execution from AI-assisted configuration layers. Practical examples demonstrate how AI can generate fatigue profiles, configure ramp/dwell sequences, adapt parameters to specimen characteristics, and automatically prepare standards-aligned reports.
The presentation explores the technical architecture required to maintain determinism, safety, and compliance while enabling AI collaboration. It also examines the broader impact of AI-native automation on development efficiency, knowledge transfer, and sustainability in testing environments.
Attendees will gain insights into how AI-native platforms transform materials testing from a code-centric workflow into a context-aware engineering environment.
This session introduces the concept of "vibe-coding" in materials testing - an AI-native approach where engineers define test sequences, operational logic, reporting structures, and machine behaviors through structured natural language. Using the Model Context Protocol (MCP), AI systems interact with machine controllers and datasets within clearly bounded operational contexts, enabling safe and traceable configuration of automation workflows.
Rather than replacing deterministic real-time control, this architecture separates critical control execution from AI-assisted configuration layers. Practical examples demonstrate how AI can generate fatigue profiles, configure ramp/dwell sequences, adapt parameters to specimen characteristics, and automatically prepare standards-aligned reports.
The presentation explores the technical architecture required to maintain determinism, safety, and compliance while enabling AI collaboration. It also examines the broader impact of AI-native automation on development efficiency, knowledge transfer, and sustainability in testing environments.
Attendees will gain insights into how AI-native platforms transform materials testing from a code-centric workflow into a context-aware engineering environment.