Zerynth is an Italian deep-tech company developing an IIoT platform for the rapid and scalable digitization of industrial manufacturing. It is currently evolving its solution into an “Industrial AI Copilot” platform equipped with a conversational agent for natural interaction with data and production processes. The development of this artificial intelligence component is considered strategic for the company’s product evolution and future positioning.
The Problem
Setting up an industrial monitoring system or changing production parameters often requires specific technical expertise and time spent working with complex software. This “barrier to entry” slows down operations and increases the risk of manual errors.
The challenge of our experiment was clear: to make the factory not only responsive but also self-configurable through natural language.
The Solution and Technologies
For this project, we developed a modular architecture based on Agentic AI. Unlike a standard chatbot, this system is equipped with “digital hands” (via APIs and MCP protocols) that allow it to interact directly with the Zerynth platform.
Here are the three technological pillars of the solution:
- Agent Orchestration: Using the Agno framework to manage agents specialized in various tasks, ranging from cost analysis to device configuration.
- Cloud-to-Edge Integration: Using Zerynth’s Jobs APIs, text input is translated into a physical command sent directly to the on-machine IoT gateway.
- Rules Engine Automation: AI is capable of autonomously writing alarm and automation rules, translating the operator’s intent into correct technical syntax.
Interacting with heavy machinery requires extreme caution. For this reason, the system incorporates AI Safety and Explainable AI (XAI) logic. The agent never executes a critical command on its own: the system pre-compiles the action and always requires explicit confirmation from the user (Human-in-the-loop). Furthermore, each action is accompanied by an explanation of why the system is suggesting it, drastically reducing operational risk.
Test Results
Validation in the demo environments and at the MADE competence center showed exciting results, but also highlighted the challenges of the future:
- Contextual Accuracy: AI excels at understanding time-related requests (“this week”) and complex filters (“only the presses on Line A”).
- Digitization of manuals: We have found that managing manuals with a large number of images requires advanced preprocessing to ensure that critical details are not lost during conversion to text for the RAG system.
- Name mapping: It is essential that the AI knows that “the big press” corresponds to the technical ID “PR-094”—a semantic mapping effort in which we continue to invest.
Benefits for the Company
The success of this phase of the AI-MATTERS project opens the door to a factory where:
- Efficiency is just a voice command away: Less time wasted on configuration, more time for strategy.
- The technology is inclusive: Even staff with limited software experience can safely manage complex configurations.
- The interaction is proactive: The system does not wait for commands, but suggests changes to the parameters based on energy costs or production loads.
The collaboration between AI-MATTERS and Zerynth is proving that conversational control is the key to democratic and secure digitization. The factory of the future is not commanded by codes, but by dialogue.