Okładka: Local RAG in the factory: Phi-4 + sqlite-vec on Jetson Orin — an MES assistant without cloud data leakage

Local RAG in the factory: Phi-4 + sqlite-vec on Jetson Orin — an MES assistant without cloud data leakage

After a year of GPT-4 and Claude pilots in manufacturing, the honest question comes back: do we really have to ship process data to the cloud to get an MES assistant? In 2025–2026 the answer is no. Phi-4 (14B, Microsoft, MIT) at 4-bit quantization fits in 8 GB of VRAM, sqlite-vec gives you vector search in a single file with no server, and a Jetson Orin NX/AGX delivers 100–275 TOPS on the shop floor. This article walks through the concrete architecture, token-per-second benchmarks, 3-year TCO vs the OpenAI API, and what this means for AI Act, NIS2 and plant-level IT operations.

Czytaj więcej
Okładka: EU AI Act, August 2026: which MES functions qualify as "high-risk AI" — and what it means in practice

EU AI Act, August 2026: which MES functions qualify as "high-risk AI" — and what it means in practice

On 2 August 2026, the EU AI Act high-risk rules become fully enforceable. A subset of MES functions — predictive maintenance tied to machine safety, operator performance monitoring, AI in medical-grade quality control, and AI-assisted workforce decisions — may be classified as high-risk, with fines up to €15M for breaches. This article maps concrete MES modules to Annex I and Annex III, lists the seven obligations of high-risk operators, and gives a 3-month action checklist for plant owners.

Czytaj więcej
Okładka: Model Context Protocol (MCP): the new standard for AI integration with MES systems. How to open production data to LLM agents without vendor lock-in

Model Context Protocol (MCP): the new standard for AI integration with MES systems. How to open production data to LLM agents without vendor lock-in

Model Context Protocol (MCP), released by Anthropic in November 2024 and adopted in 2025 by OpenAI, Google and Microsoft, has become the de facto standard for connecting LLM agents to external data and tools. For the MES world, it ends the era of "one integration per model" and starts an architecture in which a plant exposes its data once — and Claude, ChatGPT, Gemini, and home-grown agents all plug in. This article explains how MCP works, what to expose from an MES, how to design it safely (lethal trifecta, IT/OT zoning), and when MCP simply does not make sense.

Czytaj więcej
Okładka: Redash in OmniMES: Dashboards on MongoDB with SQL and REST API

Redash in OmniMES: Dashboards on MongoDB with SQL and REST API

One of the recurring questions on MES projects is: how do you build analytical dashboards on data that lives in MongoDB, without rewriting the backend to a SQL database? In OmniMES we use Redash for this — for two reasons. First, Redash can consume a REST API as a data source. Second, it has a Query Results mechanism that lets you write full SQL on the result of any earlier query. The outcome is a combination that proves to be a game changer for many MES deployments: full SQL power (JOIN, CTE, window functions) over a NoSQL backend, with zero changes in the production layer. This article walks through the setup step by step — from configuring Redash, through querying the OmniMES REST API, to a SQL query that computes a vibration trend and a ready dashboard.

Czytaj więcej
Okładka: From Industry 4.0 to 5.0: How Human-Centric AI Is Redefining the Operator on the Production Floor

From Industry 4.0 to 5.0: How Human-Centric AI Is Redefining the Operator on the Production Floor

Industry 4.0 promised a "factory without people." The European Commission, the WEF, and a growing number of manufacturers are answering with Industry 5.0 — where the human stays on the floor but gets new tools: a cobot, an AI assistant, an exoskeleton, augmented reality. The 2026 operator is no longer the person handing over a component — they process information, supervise systems, and participate in decisions. This article shows how 4.0 and 5.0 actually differ, what the market data looks like (BCG, McKinsey, EU Joint Research Centre), who is really deploying human-centric AI (Bosch, Stellantis, Airbus), and where the barriers are — cognitive fatigue, compliance with ISO 45001 and the EU AI Act.

Czytaj więcej
Okładka: Agentic AI in Manufacturing: How Autonomous Agents Take Over the Factory in 2026

Agentic AI in Manufacturing: How Autonomous Agents Take Over the Factory in 2026

Agentic AI is the next stage after generative AI. An agent does not just answer questions — it plans tasks, calls tools, adjusts line parameters, and reports the outcome. In 2026, the first factories are handing real operational decisions to agents: scheduling, maintenance planning, energy optimization. This article explains how an agent differs from a classical chatbot, which manufacturers have moved beyond pilot, what Gartner, McKinsey and Deloitte data actually says, and where the real barriers sit — control, auditability, and integration with MES/ERP.

Czytaj więcej
Okładka: Physical AI: Humanoid Robots on the Production Floor

Physical AI: Humanoid Robots on the Production Floor

Humanoid robots have moved past the trade-show demo. In the last twelve months they have appeared on BMW assembly lines, in Amazon warehouses, and in Mercedes-Benz pilots. Physical AI — the software layer that lets a machine perceive the physical world, reason about it, and act on it — is reshaping how manufacturers think about automation. This article walks through where humanoids actually stand in 2026, what the market data really says, which companies have moved beyond pilots, and where the demo ends and real production begins.

Czytaj więcej
Okładka: AI Agents in Industry 4.0: From Automation to Autonomy

AI Agents in Industry 4.0: From Automation to Autonomy

Agentic AI is redefining the trajectory of Industry 4.0. Traditional systems have largely been reactive—analyzing data and supporting human decision-making. Today, a new paradigm is emerging: autonomous agents that independently make decisions, optimize processes, and adapt to changes in real time. In modern smart factories, these systems integrate with MES, IIoT, and ERP platforms to create self-optimizing environments. Machines no longer wait for instructions—they identify issues, anticipate disruptions, and act before production is affected.

Czytaj więcej
Okładka: Data as the Foundation of Industry 4.0

Data as the Foundation of Industry 4.0

The concept of Industry 4.0 is based on continuous monitoring of production processes and decision-making driven by real-time data. Without reliable information, it is impossible to implement predictive maintenance, energy optimization, automated planning, or meaningful OEE analysis. If data is delayed, incomplete, or inconsistent, digitalization becomes only superficial. IT systems may be in place, but they do not deliver real business value. That is why it is critical to build an architecture in which data is collected automatically, consistently, and centrally.

Czytaj więcej
Okładka: Pilot MES Implementation – How to Start and Why a Phased Approach Works Best

Pilot MES Implementation – How to Start and Why a Phased Approach Works Best

Implementing a Manufacturing Execution System (MES) rarely begins with a full-scale rollout across the entire production environment. In practice, the most effective approach is incremental—starting with a pilot implementation on a selected production line or area. This allows companies to validate the system in real operating conditions, collect data, and fine-tune the configuration before scaling across the entire machine park. More and more organizations choose a pilot not only for technical reasons but also for organizational ones. MES impacts the daily work of operators, production managers, maintenance teams, and planners. Therefore, implementation should be a controlled process rather than a one-time deployment.

Czytaj więcej
Okładka: 2026: The Year Agentic AI Transforms Industrial Manufacturing

2026: The Year Agentic AI Transforms Industrial Manufacturing

Across global manufacturing, one theme has become increasingly clear: volatility is no longer something companies plan around — it is the environment they operate within. Manufacturers today face a complex combination of challenges: geopolitical uncertainty, ongoing supply-chain disruptions, increasing regulatory pressure, rising customer expectations. Each of these forces affects the entire production cycle — from planning and procurement to execution and delivery. In such conditions, organizations that have built strong digital foundations gain a significant competitive advantage.

Czytaj więcej
Okładka: AI in manufacturing: the real issue isn’t 90% accuracy. It’s data maturity.

AI in manufacturing: the real issue isn’t 90% accuracy. It’s data maturity.

In Industry 4.0 and 5.0 discussions, a common argument appears: AI models reach around 90% accuracy, and in industrial environments a 10% error can cost millions. The reasoning sounds compelling because it is framed numerically and linked to operational risk. However, this argument assumes something critical — the existence of a fully digitized factory. In reality, across many manufacturing plants in Poland and Europe — especially in the SME sector — that level of digital maturity simply does not exist.

Czytaj więcej
Okładka: The Physical AI Revolution: How Networks Power the Age of Intelligent Machines

The Physical AI Revolution: How Networks Power the Age of Intelligent Machines

Picture a warehouse robot navigating the aisles at full speed, or a port crane stacking containers with millimeter-level precision. These aren't machines running pre-written scripts — they're AI systems making decisions in real time. This is what the era of Physical AI looks like. Physical AI refers to intelligent systems capable of sensing, interpreting, and acting in the real world. Autonomous vehicles weaving through city traffic, robotic arms assembling components with surgical accuracy, smart energy grids responding instantly to load changes — these are just a few examples.

Czytaj więcej
Okładka: How MES Systems Feed Digital Twins in NVIDIA Omniverse with Production Data

How MES Systems Feed Digital Twins in NVIDIA Omniverse with Production Data

Digital twins are increasingly appearing in modern factory strategies. Process simulations, virtual production lines, scenario testing without the risk of stopping production – this sounds like the future of manufacturing. One of the most recognizable tools in this area is NVIDIA Omniverse. The problem begins when a digital twin is supposed to stop being a visualization and become a reflection of actual production. For this, data is needed. And this is where MES-class systems play a key role.

Czytaj więcej
Okładka: AI Revolution in Industry: Breakthrough Technologies of January 2026

AI Revolution in Industry: Breakthrough Technologies of January 2026

January 2026 marked a pivotal turning point in the development of artificial intelligence. AI is evolving from an “interactive tool” into a “physical entity” capable of fundamentally transforming all industrial sectors—especially manufacturing. Physical AI and the Robotics Era Jensen Huang, CEO of NVIDIA, announced at CES 2026 that “the ChatGPT moment for robotics has arrived,” signaling a mass transition of AI from the virtual space into the physical world. NVIDIA introduced a series of open models for physical AI, including the Cosmos models capable of understanding the world and generating action plans, as well as Isaac GR00T N1.6, dedicated to humanoid robots. The new Jetson T4000 module, based on the Blackwell architecture, delivers four times higher energy efficiency and AI compute performance compared to the previous generation, priced at USD 1,999 (for orders of 1,000 units). Global companies such as Boston Dynamics, Caterpillar, Franka Robotics, LG Electronics, and NEURA Robotics presented a new generation of robots powered by NVIDIA technologies.

Czytaj więcej
Okładka: Data Sovereignty in Manufacturing: Building Resilient, Secure, and Scalable Industrial Systems

Data Sovereignty in Manufacturing: Building Resilient, Secure, and Scalable Industrial Systems

Why data sovereignty is no longer a technical detail — but a strategic advantage As factories accelerate digital transformation, cloud platforms are often presented as the foundation of innovation. But for manufacturing environments, where every second of downtime translates directly into financial and operational losses, dependency on external cloud services introduces real risk. Data sovereignty — the ability to control where industrial data is processed, who can access it, and how it is governed — is becoming one of the most important pillars of modern manufacturing architecture. This is not a trend. It is the foundation of operational resilience, industrial AI, and competitive advantage.

Czytaj więcej
Okładka: Why Specialized Industries Are the New Frontier of Industrial Innovation

Why Specialized Industries Are the New Frontier of Industrial Innovation

For the last two decades, most digital innovation has focused on mass-market IT: e-commerce, social platforms, and office SaaS. But the largest untapped opportunities now lie in highly specialized, industrial domains — where processes are physical, regulated, and operationally critical. Manufacturing, energy, logistics, and infrastructure do not need more generic software. They need systems that understand how the real world of machines actually works. That is where the next decade of industrial innovation will be built.

Czytaj więcej
Okładka: MES in 2025: Why MES Systems Are No Longer Just "Shop Floor Systems" but the Backbone of Production Data

MES in 2025: Why MES Systems Are No Longer Just "Shop Floor Systems" but the Backbone of Production Data

System MES (Manufacturing Execution System) - If someone in 2025 still thinks of an MES system as "terminals at workstations and reports from the department," it's about as current as a fax machine in OT-IT integration. The Manufacturing Execution System has ceased being a shop floor application. MES has become the operational layer of truth between the world of automation (OT) and the business world (IT). MES systems in 2025 are operational platforms that determine whether a company thrives on availability, quality, lead time, and energy efficiency. The MES system has stopped being a cost—it has become a mechanism for steering competitiveness.

Czytaj więcej