AI use cases for Manufacturing & Production
18 documented implementations
Bosch pilots generative AI synthetic images for optical inspection in two German plants
Bosch is piloting generative AI and foundation models in two German plants, where synthetic images are used to develop and scale AI solutions for optical inspection. At Hildesheim, synthetic images have already trained the first standard systems in electric motor production; Bosch expects the approach to cut AI application planning, launch and ramp-up from six to twelve months to a few weeks.
Bosch· GermanyŠKODA's MAGIC EYE computer vision system predicts and prevents production line breakdowns
ŠKODA AUTO built MAGIC EYE, a computer-vision predictive maintenance system, using AWS Internet of Things services and in-house technology to move from a reactive to a proactive approach to assembly line breakdowns. Six cameras mounted by a conveyor frame collect nearly 450,000 photos as a car moves through the production line, and 10 artificial neural networks analyze them to detect irregularities such as dirt, loose or cracked bolts, or aluminum track damage, alerting a maintenance operator. The neural networks can recognize 14 defect types and 178 classes, and AWS lists reduced assembly line downtime and increased staff productivity among the benefits.
ŠKODA AUTO· Czech RepublicAmazon S3 · Amazon EC2 · Amazon RDS +1Siemens Digital Industries Software builds an Azure AI Teams app that translates shop-floor speech into routed problem reports
Siemens Digital Industries Software built a Microsoft Teams app for its Teamcenter product lifecycle management software that uses Azure OpenAI Service and Azure AI Foundry prompt flow to let frontline shop-floor workers report problems using natural speech in any language. The app parses informal speech, creates a summarized problem report, and routes it within Teamcenter to the appropriate design, engineering or manufacturing expert in their own language. The app, relying on Azure AI network isolation for enterprise security, was piloted with a few Siemens DI customers ahead of a planned December 2023 release, with Siemens anticipating faster issue reporting and resolution.
IFS Nexus Black's Resolve cuts fault resolution time 25% for industrial field engineers
IFS Nexus Black built Resolve, an AI assistant on Claude that helps field engineers in manufacturing, energy and utilities diagnose equipment problems by analyzing images and correlating sensor readings, using Model Context Protocol to connect to legacy industrial systems. Resolve cuts fault resolution time by 25%, and at a William Grant & Sons distillery in Scotland the predictive-maintenance deployment is expected to save an estimated £8.4 million a year at that single site by shifting technicians from reactive repairs to predicting failures before they happen.
IFS Nexus BlackClaude · Model Context Protocol (MCP) · Claude Agent SDK +1ABB Leads Shift to Autonomous Operations with Genix Industrial AI Platform on Azure
ABB built its Genix Industrial IoT and AI Suite on Microsoft Azure and Azure AI Foundry Agent Service, using a multi-agent architecture so AI agents can autonomously execute workflows across assets, operations, supply chain, energy, and emissions management. Genix Copilot lets shop-floor engineers scan a QR code on an analyzer to have AI agents pull real-time data and maintenance logs and suggest a fix, cutting troubleshooting time by 60-80%. Across ABB's customer base, Genix has improved reliability of critical assets by up to 20% and reduced unplanned downtime by up to 60%. Customer Birla Opus Paints used Genix to raise its "Right First Time" production rate from 40-45% to over 80% in its first year and cut root-cause analysis time from a week to an hour.
ABB· SwitzerlandMicrosoft Azure · Azure AI Foundry Agent Service · ABB Genix Industrial IoT and AI SuiteAMRC Uses IBM Maximo Visual Inspection for AI-Driven Manufacturing Defect Detection
The UK's Advanced Manufacturing Research Centre (AMRC) deployed IBM Maximo Visual Inspection software on an IBM Power Systems AC922 server with FlashSystem storage at its Factory 2050 facility to automate detection of faulty manufactured components, replacing manual light-beam inspection methods. The AI-optimized platform delivers 5 GB/s image-transfer speeds (versus 70 MB/s on prior on-premises infrastructure), trained an accurate vision model from about 500 images in roughly 20 minutes, and delivered a proof-of-concept for a startup customer in 5 days.
Advanced Manufacturing Research Centre (AMRC)· United KingdomIBM Maximo Visual Inspection · IBM Power Systems AC922 · IBM FlashSystem
AGCO scales employee-built AI agents with Microsoft Copilot Studio
Agricultural machinery maker AGCO Corporation used Microsoft Copilot Studio and Microsoft 365 Copilot to let employees become citizen developers building their own AI agents under central governance. After a leadership meeting where about 900 of 2,200 attendees volunteered to become agent 'makers,' the maker community grew to roughly 2,000 employees, producing hundreds of citizen-built and enterprise agents in production, and AGCO cut some quality reviews in its manufacturing workflows from weeks to about an hour.
AGCO Corp· United StatesMicrosoft Copilot Studio · Microsoft 365 CopilotWorkerbase powers real-time shop floor AI workflows on Google Cloud
German manufacturing software company Workerbase uses Google Cloud's Vertex AI and Google Kubernetes Engine to deliver real-time, AI-generated troubleshooting instructions to shop floor operators when machines report faults, translating instructions into workers' preferred languages and supporting predictive maintenance. Manufacturers including Siemens and Porsche use the platform, which also lets supervisors build low-code workflow apps in hours instead of months and integrates with legacy systems like SAP.
Workerbase· GermanyGoogle Cloud Vertex AI · Google Kubernetes Engine (GKE) · BigQuery +1
Bitron boosts EV charging station efficiency with Oracle AI solutions
Bitron Electronics, an Italian manufacturer monitoring more than 200 electric vehicle charging stations, built a conversational chatbot using Oracle AI Database with AI Vector Search, RAG, and LLMs (Cohere Command R, Meta Llama) via OCI Generative AI to unify fault tickets, technical manuals, and other data sources. The chatbot answers 85% of operator questions and helps diagnose charging station issues 5X faster, reducing downtime and maintenance time by tens of hours per month.
Sight Machine's AI scheduling agent cuts a beverage manufacturer's non-value-added production time 75%
Sight Machine integrated OptiMind, a small language model from Microsoft Research, through Microsoft Foundry to build an AI-driven scheduling agent for a major beverage manufacturer that had been replanning production schedules 10-15 times per week through manual meetings. OptiMind converts scheduling problems described in natural language, combined with real-time plant data on line speeds, changeover times, and ramp-up durations, into Mixed-Integer Programming optimization models, automatically regenerating an optimized schedule when floor conditions change. The system cut non-value-added production time by 75%, improved overall plant productivity by more than 10%, reduced changeover-related downtime by nearly 80%, cut ramp-up delays by nearly 60%, and reduced clean-in-place sanitation downtime by almost 90%, eliminating hours of manual planning work each week without adding production infrastructure.
Sight Machine· United StatesMicrosoft Foundry · OptiMind · Azure Machine Learning +2Cohu uses embedded AI to flag supply chain exceptions across a unified cloud platform
Cohu, a global semiconductor equipment company, unified finance, HR, and supply chain on Oracle Fusion Cloud Applications after multiple acquisitions left it with fragmented systems. Embedded AI supports real-time reporting across work orders and procurement and flags supply chain exceptions, while Oracle Fusion Cloud Product Lifecycle Management reviews product data for completeness and identifies process bottlenecks affecting launches.
Cohu· United StatesOracle Fusion Cloud Applications · Oracle Fusion Cloud Supply Chain and Manufacturing · Oracle Fusion Cloud Product Lifecycle Management +4Milwaukee Tool uses predictive maintenance to flag failure risks and cut unplanned downtime
Milwaukee Tool connected manufacturing and maintenance on Oracle Fusion Cloud with IoT-driven condition monitoring. Predictive maintenance capabilities flag failure risks and generate recommended work orders aligned to changeovers and micro-stops, letting teams schedule maintenance proactively rather than reactively, improving asset reliability and first-pass yield.
Milwaukee Tool· United StatesOracle Fusion Cloud Supply Chain Execution · Oracle Fusion Cloud Supply Chain and Manufacturing · Oracle Fusion Cloud Manufacturing +2Litoplas grows production with Oracle Fusion Cloud Applications
Litoplas, a Colombia-based flexible packaging manufacturer, extended its Oracle Fusion Cloud ERP deployment with Oracle Fusion Cloud Supply Chain and Manufacturing to connect operations across countries. The company increased production by 40% and improved inventory accuracy. Litoplas is now starting to use AI capabilities built into Oracle Fusion Cloud Applications for supplier questions, supplier knowledge chat, and purchase order summaries, with plans to apply AI to production sequencing, supply chain prediction, and accelerated access to operational insights.
Corning Accelerates Innovation with GenAI
Corning, a global leader in glass and ceramics, leverages the Databricks Data + AI Platform to improve manufacturing processes and product quality with advanced analytics and machine learning. Corning uses GenAI-powered chatbots and the Databricks Agent Framework to make hundreds of thousands of internal documents instantly accessible, with MLflow and model serving accelerating data scientist workflows by weeks or months.
CorningDatabricks · MLflow · Delta Sharing
HP Indigo Boosts Manufacturing Yield and Traceability with Databricks and Unity Catalog
HP Indigo migrated more than 3,500 data volumes (~10 terabytes) of disparate ERP, manufacturing and field data, previously tracked manually across spreadsheets and legacy systems, onto Databricks and Unity Catalog. Unity Catalog's built-in data lineage reduced consumable traceability time from two to three days down to about one hour. HP Indigo also built a prediction model on Databricks to optimize manufacturing parameters for one of its parts, increasing yield from 60% to 92%. Databricks AI/BI Genie provides natural-language, self-service data access for business users, replacing ad hoc requests to technical teams.
Martur Fompak International Boosts Throughput and Efficiency with Intelligent Robotics Enabled by Joule and Embodied AI
Martur Fompak International, a global automotive seating and interior systems manufacturer, deployed an autonomous intralogistics model using SAP's Joule solution and embodied AI capabilities, partnering with UK-based robotics company Humanoid. Built on SAP S/4HANA and SAP Extended Warehouse Management, the system gives humanoid robots and autonomous mobile robots real-time knowledge of tasks, storage locations, sequencing and production priorities, letting them identify, transport and deliver materials to the production line while continuously confirming actions back into SAP systems. The company has 400 daily production line feeds with 100% SAP software-driven decision making. Early results show increased throughput and fewer errors, with a future target of up to five times greater work efficiency for mass production. Martur Fompak International was named sole winner in the AI Excellence category at the 2026 SAP Innovation Awards.
Husqvarna Group Boosts Operational Efficiency with Azure Adaptive Cloud
Swedish manufacturer Husqvarna Group deployed Azure Arc, Azure IoT Operations, and Azure OpenAI Service to unify its fragmented public cloud, hybrid, and on-premises factory infrastructure and enable real-time data insights across its global manufacturing network. The rollout achieved 98% faster data deployment and 50% lower infrastructure imaging costs. Using Azure OpenAI Service, the company also built Factory Companion, an AI chatbot that gives factory teams instant troubleshooting guidance based on historical maintenance data and machine documentation, moving maintenance from reactive toward predictive.
Husqvarna Group· SwedenAzure Arc · Azure IoT Operations · Azure OpenAI Service +2Roche scales NVIDIA AI factories globally to accelerate drug discovery, diagnostics and manufacturing
Roche is deploying more than 3,500 NVIDIA Blackwell GPUs across hybrid cloud and on-premises environments in the U.S. and Europe, expanding an existing collaboration to turn AI and accelerated computing into a core operating capability across its pharmaceutical and diagnostics businesses. AI is central to Genentech's Lab-in-the-Loop drug discovery strategy, where nearly 90% of eligible small-molecule programs integrate AI; in one program a degrader molecule for oncology was designed 25% faster, and in another AI helped deliver a backup drug candidate in seven months instead of more than two years. Roche is also using NVIDIA Omniverse to build digital twins of manufacturing sites, including its new GLP-1 facility in North Carolina, uses NVIDIA Parabricks software to enable insights across vast datasets, is evaluating the BioNeMo platform for molecular design and chemistry innovation, and uses NVIDIA NeMo Guardrails to ensure safe and reliable healthcare-grade AI.
RocheNVIDIA Blackwell · NVIDIA BioNeMo · NVIDIA Omniverse +2