Digital maintenance instructions: on your phone instead of in a folder

Maintenance instructions are most useful where the work is done – on your phone in front of the installation, not on a shelf of folders back at the office. To make that work, you need three things: the documents in digital form, a central place to store them and a search that understands questions in everyday language. This guide shows step by step how companies move their manuals, service reports and installation data from paper to the phone – and is honest about the limits.

In brief

• Maintenance instructions only earn their keep when they can be accessed on site – in a folder at the office, they are no help to anyone standing in front of the installation.
• Most manufacturers’ manuals have been available as PDFs for years; as a rule, a company only has to scan its own and older documents.
• Text recognition (OCR) makes scanned folders, photos of rating plates and old reports searchable too.
• An AI-supported knowledge base answers questions in everyday language and names the source document for every answer.
• For safety-critical steps, the manufacturer’s original remains the authority – the AI answer is the quick way to it, not a substitute for it.

Why are maintenance instructions usually where nobody needs them?

The typical picture in technical companies: the office has a wall of folders – manufacturers’ manuals, installation documentation, inspection reports, neatly labelled and built up over decades. Meanwhile, the technician who needs the information is twenty kilometres away in the customer’s boiler room, puzzling over an error code.

Every service company knows what happens next: a call to the office. Someone there leafs through the folder, takes a photo of the right page and sends it to the technician’s phone. That works after a fashion – but it ties up two people every time, takes a quarter of an hour and fails completely if nobody in the office happens to pick up.

Even companies that are “already digital” are often only halfway there. The PDFs are on the server, spread across folder structures that only the person who set them up understands. But storing documents doesn’t make them findable: anyone who doesn’t know where things are kept and what the files are called will search in vain on a small phone screen.

Which documents belong in the digital maintenance file?

The digital maintenance file is the complete, searchable collection of all documents for an installation or installation type – from the manufacturer’s manual to your own service notes. Five groups cover everyday work:

Document	Typical content	Typical question on the job
Manufacturers’ manuals	Operation, maintenance intervals, error codes	“What does error code E42 mean on this boiler type?”
Your own service reports	Work carried out, parts replaced, anything unusual	“When was the circulation pump last replaced?”
Installation documentation	Rating plates, wiring diagrams, settings	“What values was the burner set to?”
Inspection and acceptance reports	Measurements, conditions, defects found	“What was flagged at the last inspection?”
Spare parts and supplier lists	Part numbers, suppliers, delivery times	“Which valve fits, and who can deliver it fastest?”

Your own reports and notes are usually the most valuable – because they exist nowhere else. You can always get the manufacturer’s manual again if need be; but only the colleague who fitted it knows that the shut-off valve on the third-floor installation sits behind the panelling.

That is why a collection of manuals on its own falls short. Only manufacturer knowledge combined with your own knowledge of the installations answers the questions that actually come up on the job.

How do you turn folders and PDF collections into something searchable?

Getting from a shelf of folders to a searchable maintenance file is more manageable than it sounds – as long as you go about it in the right order:

1. Take stock of your documents: work out which installation types you look after and which documents you have for them – on the shelf, on the server, in mailboxes.
2. Get the manufacturers’ PDFs: most manuals from the last fifteen years are available as PDFs from the manufacturer. Downloading is quicker than scanning.
3. Digitise your own material: scan service reports, installation sheets and important older documents; text recognition (OCR, which automatically turns images into searchable text) makes them searchable.
4. Bring everything together: store everything in one place, with clear names by installation type or customer – instead of scattering it across drives and mailboxes.
5. Make it searchable and test it: add the collection to an AI knowledge base and use real questions from everyday jobs to check that the answers and their sources are correct.

The practical guide to the AI knowledge base shows what this looks like in practice at various companies – from loading the first documents to everyday routines.

What do you gain from asking questions in everyday language on your phone?

The real difference shows on the job. The technician types into his phone the question he would otherwise have phoned through to the office: “What maintenance intervals apply to the type X ventilation system?” or “What was unusual at the last service of the installation at the lakeside hotel?” The answer comes back quickly – written from your own documents, with the source document named.

The source is more than a nice extra. An AI can be wrong, so every answer must be checkable: one tap opens the original document at the right passage. For safety-critical information – pressures, torques, isolation procedures – checking the original is mandatory, not optional.

In everyday work, the effect adds up: fewer calls back to the office, shorter jobs, fewer return visits because information was missing. And new technicians can ask questions without tying up an experienced colleague for every task. junova’s product page describes how such a knowledge base works – with data stored on EU servers and without your documents being used to train third-party AI models.

What are the limits of the digital maintenance file?

It is only fair to be honest about them: the technology makes documents findable, not better. An outdated manual stays outdated, an incomplete service report stays incomplete – keeping the documents up to date is still work the company has to organise.

Text recognition has its limits too. Printed manuals and clean scans work reliably; scrawled handwriting on yellowed installation sheets, on the other hand, is often only partly recognised. In such cases it helps to add the key information briefly when you scan the document – one line of context turns a silent scan into a document people can find.

Finally, there is mobile reception: in a basement with no signal, even the best database can’t help. For jobs in dead spots that you can plan ahead, download the relevant documents beforehand – a step that is as much a part of preparing for the job as packing the tools.

How do companies get started without a major project?

The most common mistake is trying to digitise thirty years’ worth of folders in one go – that overwhelms any team and fizzles out after three weeks. The opposite approach has worked well: start with the twenty installation types that generate the most questions, and add to the collection bit by bit as day-to-day business goes on.

That way the benefit shows up first where it saves the most time – and the team sees early on that recording things is worth the effort. The implementation process for the AI knowledge base shows how the introduction works in practice, from the intro call and loading the first documents to the first real questions about your own documents.