Skip to content
Service & spare partsPumps & ValvesElectronics & SensorsWater & EnvironmentMachinery & Plant Engineering+2

Remote diagnosis from log files and condition data

demi analyses exported logs and condition data, compares them with past cases and proposes the cause and the fix.

Today

Customers send log files and condition data, but only a few experts can read them, if anyone does. The site visit is planned without a diagnosis. The technician starts searching at the machine and often brings the wrong part.

An example

A customer of Ebert & Lorenz Maschinenbau sends the log export of a 250 kN press. The agent finds repeated overcurrent warnings on axis 2, each shortly after a tool change, and links them to 4 past cases caused by a worn cable carrier. The technician reviews the diagnosis and drives to the customer with a new cable carrier.
Fictional company, typical workflow.

Your data, wherever it lives

Today log files and condition data arrive as e-mail attachments, as uploads to the customer portal or on a file share, the software release notes sit as PDFs and past failure cases in the CMMS. demi reads, understands and links them per machine, configuration and software version, with your rights. The AI finds patterns in thousands of log lines in minutes instead of hours and proposes a cause, and a technician reviews the diagnosis before it goes to the customer.

Where the data lives today

  • Machines & sensors
  • E-mails
  • Web & portals
  • Folders & drives
  • PDFs
  • Tickets
Data LayerOne view of everything, with your rights

How demi solves it

Three layers in this order: connect the data first, then the rights, then the AI.

  1. 1 · ConnectData Layer

    The case needs data from the CMMS, file share, e-mail and portal. demi replaces nothing and links exported logs and condition data to the machine, its configuration, software release notes and past failure cases. demi writes back only after approval.

  2. 2 · PermitPermission Layer

    Customer data stays in that customer's case, and only the service team of the responsible region has access. A technician reviews and approves the diagnosis before it goes to the customer, and this is recorded.

  3. 3 · ActIntelligence Layer

    The agent detects known patterns and anomalies in the logs and drafts a diagnosis with a confidence rating. It quotes values and time stamps verbatim with the log line and case behind them, and it never controls the machine.

How it runs

  1. 1

    Take the log export from the portal, e-mail or file share

  2. 2

    Link the logs to machine, configuration and software version

  3. 3

    Find known patterns and anomalies

  4. 4

    Compare with past cases and draft a diagnosis

  5. 5

    Have a technician review it, then plan the visit and the part

What changes

  • Fewer unnecessary site visits

  • Technicians arrive with the right part

  • Cases resolved faster

What does it bring you?

Check it with your own numbers

Every starting value is an assumption you can change. The calculation sits right below, step by step.

Assumption, editable

Your numbers

Result

+324 hfreed per year

Assumptions and calculation

demi analyses the logs, compares them with past cases and proposes a cause; you set the action.

90 min → 63 min per case

How does it run today?

What is already digital saves less: the factor lowers the share demi brings.

How we calculate

60 remote diagnoses × 90 min × 30% × 1.0 (manual) × 12 months = 19,440 min = 324 h

Value per year, before demi costs

Freed per year+324 h

Assumption: labour cost of €49.50 per hour in German manufacturing in 2025 (Destatis), plus workplace, IT and overheads.

= Value per year, before demi costs

+€21,060

gained per year

324 h ÷ 1,760 h per role = 0.2 full-time roles

An estimate, not a promise. The starting values are assumptions for an industrial company with 150 to 500 people.

Combine with more cases and get the package

Questions about this use case

Does demi control the machine?

No. demi only reads data the customer exports or your portal provides. There is no access to the controller and no commands to the machine. What happens at the machine is decided and done by your technician.

Which log formats can demi read?

Text and spreadsheet exports, structured formats and the exports of common controllers and condition monitoring systems. For a proprietary format the agent derives the structure from samples and your documentation, and your team confirms it once. Anything it cannot interpret with confidence, it flags instead of guessing.

How is our customers' data protected?

Each log export stays in its customer's case and is visible only to the responsible service team. To compare with past cases the agent uses findings and patterns without carrying customer data into other cases. The data stays in the EU.

How reliable is the diagnosis?

For every diagnosis the agent states how confident it is and why: which log lines, which past cases. If nothing known fits, it says so plainly. A technician reviews the diagnosis before it goes to the customer or a visit is planned.

See this case with your data

In the demo we show you the workflow on your own systems.

Your configurator

No use cases yet

Your configurator is still empty

Add a use case from any card or case page and see what it brings per year, with the calculation. Free, no sign-up, no commitment: try it out and change any number.

Browse use cases