Velotic has added agentic AI capabilities to its ThingWorx Industrial Intelligence Platform with ThingWorx 10.2. The release includes ThingWorx AI Assistant, ThingWorx MCP Server, and AI & Agent Services. Velotic calls them an "enterprise foundation" for building secure, extensible AI assistants and agents that work with industrial data, context and existing systems.
The MCP server is the most concrete piece. With support for Model Context Protocol, ThingWorx can create MCP servers for legacy systems, giving AI agents access to operational data and context from systems "never designed to work with AI," according to Velotic. ThingWorx already models those environments for industrial applications, so developers building assistants and agents start from that existing context.
For automation and manufacturing engineers, the practical question is whether an agent can reach older equipment and applications without a replacement project. Velotic's product page says ThingWorx wraps and extends existing systems, MES included, rather than replacing them.
"Manufacturers don't need another disconnected AI environment. They need intelligence that can understand and work with the operations they already have," said Chris Balwin, chief product officer at Velotic.
Shashi Preetham, CEO of PSPTechHub, an IT services and consulting company focused on industrial digital transformation, said the 10.2 features let factory teams "ask questions in plain language, investigate problems faster, and spend less engineering time searching through data."
The release also updates the platform's industrial applications, including Connected Work Cell and Real-Time Production Performance Monitoring. Velotic lists MQTT v5 support among the other changes in ThingWorx 10.2, along with updates to device management and security.
