EAM Boutique
Senior EAM expertise with AI-assisted implementation: clarify the process, define precise changes, verify the result and hand over documented work.
View pathEAM · interfaces · AI & ML
Improve EAM. Connect systems. Apply AI where it adds value
I improve EAM workflows, build and stabilise interfaces between business systems, and develop focused AI/ML solutions around real data and decisions. Each capability is available on its own.
Work directly with me from the first concrete example through implementation, testing and a documented handover.
Three capabilities
Three capabilities, available separately
Choose the expertise your problem needs. Each area has a clear starting point and can be commissioned independently or combined within an agreed scope.
Interface Engineering
Repair existing data flows or build a defined new connection across business systems, with agreed mapping, error handling and acceptance tests. Independently available without EAM.
View pathApplied AI & Machine Learning
Computer vision, sensor and time-series ML, document intelligence and decision support—built as focused pilots, tested against measurable criteria and kept within human guardrails.
View pathExperience and examples
See the work behind the offer
My EAM experience includes leading a six-person company before COVID, clarifying customer processes and guiding implementation. Published demonstrations and self-initiated projects show how I work today.
Published EAM demonstration
Configuring an EAM inbox
A recorded example of AI carrying out EAM configuration through the browser under expert direction. Customer access, review and release controls are agreed for each engagement.
Watch the EAM inbox demoSelf-initiated ML projects
Water pressure and hoof images
Sensor time-series and computer-vision prototypes, both still active in adapted forms. The project descriptions explain the data, model tasks and limits of the results.
Explore the two ML prototypesPublished workflow demonstration
An AI assistant inside Excel
An Excel task-pane agent that works directly in the workbook. The demo shows the workflow; ongoing development explores how it can support practical spreadsheet work.
Watch the Excel agent demoHow I work
From the problem to a tested next step
The work starts with evidence: a work order, interface record, data sample, document, report or manual handover. The goal is to decide what should change, test it against real cases and document the result.
01
Start with the real bottleneck
Unclear work orders, unreliable interfaces, poor data, a manual workflow or one defined AI/ML opportunity.
02
Build or specify the smallest useful change
An EAM change, interface fix, data-readiness decision, focused work app or AI/ML pilot that can be tested against real cases.
03
Make the next decision explicit
Document the logic, ownership, test evidence and handover path—then deploy, harden, integrate or stop with a clear reason.
Partner Support
Technical support for partner teams
Bring me into a defined EAM, interface, data or AI/ML work package. You retain the client relationship and programme ownership; I provide hands-on implementation, agreed tests and a documented handover.
Field notes
Field notes from systems and projects
Practical walkthroughs and full articles across the EAM last mile, interface reliability, operational systems and applied AI/ML.
From the blog
Latest articles
EAM operations
↗Closing a Work Order Is a Data Quality Decision
5 min read English
Closing a work order establishes the maintenance history that planning, reliability, costing and future decisions will treat as evidence.
- EAM
- Maintenance
- Operations
Reporting
↗Why Reports Become Shadow Systems
5 min read English
Reports are useful for visibility. They become risky when they start replacing process ownership, exception handling and operational control.
- Enterprise Systems
- Operations
- Reporting
Data quality
↗Why Master Data Is Not a Cleanup Project
5 min read English
Master data is not a one-time cleanup project. In production, it is an operating responsibility that shapes workflows, interfaces and reports.
- EAM
- Operations
- Ownership
Other channels
YouTube
Practical walkthroughs
Short demonstrations of EAM, interface behaviour, operational automation and realistic AI/ML use cases.
Open YouTube LinkedIn
Field notes and takeaways
Operational observations from EAM, interfaces, data quality, applied AI and partner delivery work.
Open LinkedIn Blog
From pilot to production
Longer notes on EAM last-mile work, interface reliability, data readiness, applied AI/ML and practical automation.
Open BlogEAM operating contexts
Where EAM meets daily maintenance
Explore EAM requirements in these asset-intensive industries. Interface engineering and AI/ML can also start in other sectors and systems.
Manufacturing & process industry When maintenance data, production pressure and system logic collide, small EAM gaps create recurring shop-floor work. See typical bottlenecks Energy & utilities Distributed assets, field work and evidence requirements make unclear data ownership and interface timing visible quickly. See typical bottlenecks Facilities & building services Service requests, SLAs, contractors and location data need to become one reliable maintenance flow instead of parallel lists. See typical bottlenecks Logistics & transport Fleet, terminal and warehouse uptime depends on clean handovers between inspections, defects, maintenance and operations. See typical bottlenecks
Explore industries Start
What is getting in the way?
It can be an EAM bottleneck, an unreliable interface, an AI/ML opportunity or a manual operational workflow. One concrete example is enough for a useful first assessment.