Industry

After-Sales Agent

The technician is at the machine. The missing part was in the history all along.

Streamlines service processes and spare parts management.

Open agent
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

STACKIT Sovereign hosting in Germany, single-tenant from the first user.
Rödl Legal, tax and compliance expertise for legally sound deployment.
4P Consulting Advisory and implementation for the public sector, starting with the AI readiness assessment.

Two call-outs for one fault, because the part was not in the van the first time.

The ticket comes from the hotline with the customer's description of the fault; the machine history sits in the service ticketing system, the parts stock in the ERP. Whoever schedules the job would need to bring the two together before the technician sets off. If not, the visit ends with a parts order and a second call-out.

1fault reportThe customer reports a filling line failure to the hotline.
3previous visitsThe system holds three service reports on the same assembly from the last 18 months.
2likely partsThose reports point to two parts that will be needed on site.
21 dayslead timeOne of the two parts is not in the service warehouse and has to be ordered in.

The service manager sees the 21-day lead time at the point of scheduling, and that is where the 30% faster service turnaround comes from: the technician makes one trip, with the seal kit and pump head in the van.

The 30% faster service turnaround is this agent's headline figure. Three prior reports on one assembly and a 21-day lead time for one part describe an ordinary service case; they are not measurements.

Three steps through the process.

The agent reviews service reports, machine data and stock together; the service manager decides whether a technician goes out, and with which part.

Retrieve earlier visits to the assembly

For the reported machine, the agent finds the earlier service reports and the fault messages logged by the controller. It lists the visits to the same assembly by date.

Machine AB-4471, 3 visits to the dosing pump since 02/25

Check likely parts against stock

From the earlier reports, the agent derives the parts likely to be needed and looks them up in the ERP. Missing parts are shown with their lead time.

2 parts earmarked, seal kit in stock, pump head with a 21-day lead time

Pass the job proposal to scheduling

The agent combines ticket, history and parts list in one overview and notes what can be supplied from stock. The service manager schedules the job on that basis.

einsatzvorschlag_AB-4471.pdf, 2 parts, 1 open procurement

What the agent does not do.

It does not order spare parts.

It shows the requirement and the lead time. Service scheduling places the order in the ERP.

It does not decide whether the damage is covered by warranty.

It names the installation date, running time and the previous visits to the assembly. The after-sales manager settles warranty and goodwill.

It only knows about modifications at the customer's site if they were reported back to the machine file.

For machine AB-4471, the state recorded in the service reports is what counts. If the dosing pump was swapped on site for a different make, the technician will find an assembly that does not match the job proposal, and records it in the file after the visit.

Connected systems

  • ERP
  • service ticketing system
  • machine data acquisition

Operations

  • Deployment modelEU cloud or private cloud
  • Data processingGDPR-compliant, no model training on your data
  • Responsible teamsService, after-sales

The questions that come up before the first meeting.

How quickly is the After-Sales Agent ready to use?

A pilot typically runs on your own data within 6 to 8 weeks. The agent connects to your existing systems rather than running as a separate, parallel environment.

Where is the data processed?

EU cloud or private cloud. Processing is GDPR-compliant and models are never trained on your data. Details in the Trust Center.

Where does the figure “30% faster service turnaround” come from?

It is based on experience from comparable projects and process benchmarks, not a commitment. We establish the realistic effect for your organisation in the assessment before the pilot.

Related agents.

Intake review, case 2026/04711

Skip to content

Page footer