Industry

Servicing Planning Agent

A bearing that has been getting louder for weeks is in no maintenance plan.

Optimises maintenance cycles from operating data and reduces downtime.

Optimises maintenance cycles from operating data and reduces downtime.

Open agent

Enlarge demo

Public administration

Four processes that take up the most time today

Developed in Germany · Hosted in the EU

Developed in Germany · Hosted in the EU or on-premises

Delivered together with

Sovereign hosting in Germany, single-tenant from the first user.

Sovereign hosting in Germany, single-tenant from the first user.

Legal, tax and compliance expertise for legally sound deployment.

Legal, tax and compliance expertise for legally sound deployment.

Advisory and implementation for the public sector, starting with the AI readiness assessment.

Advisory and implementation for the public sector, starting with the AI readiness assessment.

An unplanned stoppage costs a shift that the rest of the week cannot make up.

The press fails in the middle of the late shift. Neither the spare part nor the technician is on site, so the order moves to the backup machine, which runs more slowly. The note about the rising bearing temperature had been in the log for three runs, but nobody read it in context.

26

machines

Twenty-six machines in the plant each have their own maintenance cycle.

3

early warnings

On press PR-14, temperature and running noise rise over three runs.

1

bearing failure

The damage brings the machine to a halt in the middle of the late shift.

9 hours

of downtime

Sourcing the spare part and the repair take up nine hours that no shift can make up.

The path to 20 to 30% fewer unplanned stoppages starts with a maintenance order already drafted at the second temperature rise, with the sensor trend as its justification.

The 20 to 30% reduction in unplanned stoppages is this agent's headline figure. Nine hours of downtime and three early warnings at the press describe a typical sequence in a plant with 26 machines; none of it was measured.

Three steps through the process.

The agent spots maintenance needs from run, sensor and log data; the head of maintenance sets the order of the jobs.

1.

1.

Read machine data for anomalies

The agent analyses run times, sensor series and the latest maintenance logs for each machine. It highlights machines whose values move in the same direction over several runs.

The agent analyses run times, sensor series and the latest maintenance logs for each machine. It highlights machines whose values move in the same direction over several runs.

Press PR-14, bearing temperature up from 62 to 78 degrees over 3 runs

2.

2.

Check the maintenance window against machine bookings

The agent checks when the machine is free in the production plan and whether the spare part and a technician are available. If the two do not line up, it names the gap.

The agent checks when the machine is free in the production plan and whether the spare part and a technician are available. If the two do not line up, it names the gap.

Window on Saturday 6 June, bearing set in stock, technician with additional qualification not scheduled

3.

3.

Submit the maintenance order for approval

The agent creates the order with machine, window, material and reasoning. The head of maintenance sets the priority order and approves it.

The agent creates the order with machine, window, material and reasoning. The head of maintenance sets the priority order and approves it.

IH-60421 in draft, proposed priority 1 of 7 open orders, reasoning with sensor trend

What the agent does not do.

It does not take any machine offline.

It does not take any machine offline.

It reports the trend and proposes a window. The head of maintenance is responsible for shutdown and order approval.

It makes no promise about how long the bearing will last.

It makes no promise about how long the bearing will last.

It shows the rise from 62 to 78 degrees over three runs. The maintenance technician on site judges how long the machine can safely keep running.

It does not assess trends for machines without sensors.

It does not assess trends for machines without sensors.

The manual press in hall 2 supplies no measurement series, so it stays on the fixed cycle from the maintenance plan. The agent keeps it on the list without a trend assessment.

Connected systems

Maintenance management system

MES machine data

ERP spare parts store

Operations

Deployment model

EU cloud or private cloud

EU cloud or private cloud

Data processing

GDPR-compliant, no model training on your data

GDPR-compliant, no model training on your data

Responsible teams

Maintenance, engineering

Maintenance, engineering

The questions that come up before the first meeting.

How quickly is the Servicing Planning Agent ready to use?

Where is the data processed?

Where does the figure “20 to 30% fewer unplanned stoppages” come from?

Related agents.

All agents

Platform

Industries

Services

Resources

Company

Pricing

From AI strategy to a running platform: we show you the way.

Talk to us

Log in

DE

EN

English

Platform

Industries

Services

Resources

Company

Pricing

From AI strategy to a running platform: we show you the way.

Talk to us

Log in

DE

EN

English
neuland.ai

The AI management and orchestration platform from Cologne.

Developed in Cologne. Operated in the EU or in your data center.

Certifications and compliance: ISO 27001, ISO 9001, GDPR, EU AI Act, DORA, StBerG, and BRAO
WirtschaftsWoche Best of Technology 2026 seal, 2nd place in the Process Management category for neuland.ai

© 2026 neuland AI AG