Featured/13 August 2026
How to prevent knowledge loss when an expert leaves
A maintenance expert is retiring: how to capture their expertise in six months, what to prioritise first, and the checklist from D-180 to D-0.
Read the article →Use case
Failures at restart after the annual shutdown: why?
After an annual shutdown, faults cluster at restart. What the shutdown changes on the machine, and how to keep a record of the work done.
Read →Pain point
The hidden time spent looking for information in maintenance
Before repairing, a technician searches: the right drawing, the right history, the right expert. That invisible time is expensive, and easy to win back.
Read →Field
Industrial maintenance AI agent: a definition
A maintenance AI agent is software that reasons about a fault to guide diagnosis and decision, beyond prediction. A clear definition.
Read →Pain point
Do your identical machines learn from each other?
A fleet of identical machines should pool faults and fixes. Too often each one stays an island. How to connect knowledge across a homogeneous fleet.
Read →Legal & market watch
Agentic AI: 4 in 10 projects abandoned by 2027
64% of technology leaders are deploying agentic AI within two years, yet Gartner expects 40% to be abandoned. What separates the ones that last.
Read →Pain point
Is your 20 years of CMMS history sleeping for nothing?
Years of failure history pile up in the CMMS and never get used. How to wake up data you have already paid for and anticipate recurring faults.
Read →Legal & market watch
CMMS and AI under the AI Act: what Article 14 requires
Article 14 of the AI Act requires human oversight of high-risk AI. What it demands from a CMMS and AI deployment, and the point most vendors miss.
Read →Pain point
The industrial memory crisis: when the factory forgets
When the factory loses its maintenance lessons: how the industrial memory crisis paralyses your operations, and how to structure it.
Read →Use case
Supporting the maintenance technician alone at night
On a three-shift rota, the technician faces the breakdown alone, with no expert at night. How to structure the diagnosis and capitalise on it.
Read →Pain point
The real cost of unplanned downtime in industry
Beyond the part and the labour, what unplanned downtime truly costs, and how a faster diagnosis changes the picture.
Read →Use case
Integrating CMMS / ERP into an existing information system
Integrate a CMMS or ERP into an existing information system without a full rebuild: the lightweight approach that reads your systems in place.
Read →Field
ERP or CMMS for maintenance: what are the differences?
ERP or CMMS for maintenance? The differences, how the two tools complement each other, coupling them, and making the most of what you already have.
Read →Field
AI assistant for maintenance technicians: what works
An AI assistant for field maintenance technicians: market promises, what genuinely helps on site, and what is just marketing.
Read →Pain point
Condition-based maintenance: acting at the right moment
Vibration, oil, temperature, cycles: which signals to monitor to intervene at the right moment, and when condition-based maintenance is worth the effort.
Read →Field
Intervention reports by voice instead of typing
How AI automatically generates your intervention reports from voice dictation. Single entry, accessible diagrams, captured know-how.
Read →Field
Preventive vs predictive maintenance: what's the difference?
Corrective, preventive, condition-based and predictive: the full picture of maintenance strategies, their limits, and how to choose.
Read →Field
The 5 mistakes that kill an industrial AI project
A large share of industrial AI projects fall short of their goal. The 5 mistakes that kill them, and how to avoid them, on method and on the ground.
Read →Field
Symptom or root cause: are you fixing the right problem?
Find out why treating the symptom without identifying the root cause is costly for your maintenance. Complete guide and concrete cases.
Read →Field
The relational graph: mapping the machine from diagrams
A relational graph turns your electrical, pneumatic and hydraulic diagrams into a navigable map of components, for safer diagnosis.
Read →Field
Digital twin or sensors: which to choose for maintenance?
A functional digital twin is built without sensors, from your diagrams. What sets it apart from sensor-based predictive maintenance, point by point.
Read →Field
How AI models your equipment from electrical diagrams
AI modelling of industrial equipment turns your electrical diagrams into a functional digital twin, for a structured diagnosis.
Read →Legal & market watch
Three world visions of AI: innovation, control and trust
United States, China, Europe: three visions of AI shaping regulation and industrial adoption. A briefing for decision-makers.
Read →Use case
Trust and control: the real levers of ROI in industrial AI
Trust, control, knowledge capture: the three real levers of ROI for an industrial maintenance AI, beyond the promises of algorithms.
Read →Field
Functional digital twin: maintenance without sensors
The functional digital twin models your equipment as a navigable graph (components, diagrams, failures) for guided diagnosis, with no sensors and no 3D.
Read →Field
An immune system for your machines against failures?
How a factory develops an immune system against failures: capturing every resolved incident to diagnose faster and anticipate.
Read →Field
Field technicians, the real AI experts
Your field technicians are the real AI experts. How to capture their tacit knowledge and build a collective intelligence.
Read →Field
AI-guided diagnosis in maintenance: the complete guide
Understanding AI-guided diagnosis in industrial maintenance: principles, how it differs from attached procedures, FMEA, MTTR. Complete 2026 guide.
Read →Use case
Guided diagnosis: the augmented technician's secret weapon
How a Mimorian guided diagnosis works. From breakdown to diagnosis in 20 minutes. A concrete example: a Schneider ATV930 drive failure.
Read →Legal & market watch
AI Act May 2026: impact on industrial maintenance
AI Act agreement of 7 May 2026: industrial AI leaves the dual regime but stays under the Machinery Regulation. What changes, what remains mandatory.
Read →Field
ChatGPT vs orchestrated AI in industrial maintenance
ChatGPT in industrial maintenance: useful for Q&A, limited for diagnosis. Comparison with an orchestrated multi-agent AI built for the plant.
Read →Legal & market watch
EU AI Act and industrial maintenance: compliance 2026-2028
The 7 May 2026 Omnibus agreement, the 2026-2028 timeline and its link with the Machinery Regulation. Decoded for industrial maintenance, without alarmism.
Read →Pain point
Loss of know-how in industrial maintenance
The shortage of technical talent is accelerating as experts retire. How to structure your experts' know-how before it disappears.
Read →Field
Capturing maintenance know-how: the complete guide
Your experts are retiring and taking their know-how with them. Methods to capture field know-how in maintenance before it disappears.
Read →Field
Trustworthy AI for industrial maintenance: the guide
What is trustworthy AI for critical operations in industry? The 6 pillars, the AI Act, data quality and the concrete criteria to look for.
Read →Field
Trustworthy AI is not perfect AI
Trustworthy AI is not perfect AI. Discover why transparency and human supervision are the keys to adoption in maintenance.
Read →Field
Trustworthy maintenance AI starts with reliable data
Without reliable data, no trustworthy AI in industrial maintenance. Customer case: diagnosis cut from 3 hours to 15 minutes with Mimorian.
Read →Legal & market watch
The six pillars of trustworthy AI
Robustness, transparency, data governance: discover the 6 pillars of trustworthy industrial AI according to the European Commission and the AI Act.
Read →Field
Make the most of the field know-how MES forget
MES run production but overlook field knowledge. See how to capture technicians' expertise with Mimorian.
Read →Field
Industrialising the collective memory of maintenance
Field knowledge is lost with every departure. See how to industrialise collective memory in maintenance with industrial intelligence.
Read →Field
Recurring failures: the invisible cost of lost know-how
Recurring failures cost dearly for want of knowledge capture. How to structure field feedback so the same fault is never diagnosed twice.
Read →Legal & market watch
Industrial AI: from symbolic systems to deep learning
From Dartmouth 1956 to the Transformers: retrace a century of AI at speed and understand why it is transforming industrial maintenance today.
Read →