Use Case · Product Management & Application Engineering · 2026

How product data becomes reliable sizing.

A pump and component manufacturer, product management and application engineering · ~50 products and variants · POC in one week.

The right variant with standard and proof, consistent for sales and trade.

Download the use case as PDF →

Baseline

Broad portfolio. Sizing knowledge in a few heads.

Drum pumps, container pumps, variants in PP, PVDF and stainless steel – across many media. Which variant fits which application is known to a few experts.

Products & variants~50across the portfolio

Material lines3PP · PVDF · stainless

Sizing queries / year~150from sales & trade

Of which standard~60 %recurring

Representative profile. Aggregate figures are model assumptions; the products and the example below come from real product and service data.

Problem

Three ways today. None gives consistent sizing.

Every query is answered by whoever is available. The result: wrong variant in the quote, complaint in the field, different answers outward.

Way 1Guess from the catalog

wrong material variant
complaint in the field
tuition fee per order

Way 2Dig through old quotes

scattered, no index
reasoning not findable
inconsistent outward

Way 3Ask the expert

application engineering becomes help desk
not scalable
knowledge stays in the head

A wrong material choice costs not only the complaint, but the customer's trust. And with staff turnover, the why behind the decisions disappears.

Architecture

How the agent is built.

Four modules – from reading product data to backed-up sizing. Not a new tool, but structured processing of what is already there.

Input · existing data sources

Product dossiersStandardsOld quotesService cases

↓

Module 01Reader

Reads and extracts from product dossiers, datasheets, standards and quotes. Captures core data and media suitability.

I/O · raw data → structured text

↓

Module 02Classifier

Recognizes suitability attributes: medium, material, pressure, temperature, certification, variant.

I/O · text → fields with values

↓

Module 03Dossier builder

Builds a suitability matrix per variant, with proof from standard, quote and service case, including exclusions.

I/O · fields → complete dossier

↓

Module 04Filter index

Makes the portfolio searchable by medium, material and application. Application engineering and sales answer in seconds, consistently.

I/O · dossiers → search index

Output · what PM, sales and trade use

Sizing with standard and proofConsistent info outwardVariant knowledge kept

Approach

POC setup in one week.

This is what the proof looks like. The POC always runs on a small, bounded data package, for example one product group. The productive implementation builds on it step by step.

Day 101Data package

Hand over one product group with datasheets and standards. IT effort: ½ day.

Day 202Criteria workshop

Media, materials, certifications and exclusion rules defined together. 2-hour workshop.

Day 3–403Agent setup

Reader · classifier · dossier builder · filter index configured. First product dossiers generated.

Day 504Test & handover

Validation on 5 real sizing queries. Walkthrough with PM and application engineering. Handover.

POC effort on the customer side: ½ day. At the end of the week you see what is possible. Whether and to what extent you go productive, you decide afterwards.

Output

What sales and application engineering see in the end.

Ask like in a chat, answers across multiple sources. The agent links product data, standard and field feedback, and asks instead of guessing.

Getze Knowledge Agent·Application Engineering Agent

v1.0

APPLICATION ENGINEERING AGENT

Sizing: which variant, which material, which standard.

POC · small data package

YOU

Sales / Application engineering

A customer needs a drum pump for 30 percent sulfuric acid. Which ones can we offer?

Application Engineering Agent · asks instead of guessing

Quick question: continuous duty or transfer only, and what temperature?

YOU

Sales / Application engineering

Transfer from the drum, around 40 degrees.

Application Engineering Agent

Then GP-E2 in the PVDF premium variant. The GP-E1 in PP is not approved for acids, so exclude it. Wetted material PVDF, seal FKM. For the mechanical seal use SSiC/SSiC, because carbon/WC fails in dilute sulfuric acid. For a pressure device, check the PED classification.

Source: Product dossier GP-E2 · Service case 11 · Standard PED 2014/68/EU

Ask a question

Impact

Sizing in seconds. Consistent outward. Knowledge kept.

Three measurable effects once product, standard and experience are available from one source.

Sizingwith proofright variant with reasoning instead of gut feeling.

Sales & tradeconsistentthe same reliable info for all, regardless of contact.

Knowledgeindependentvariant knowledge available, even without the expert.

Use case as PDF

Download the full use case.

Including architecture, the full sizing example across multiple sources and impact. You get the PDF right after submitting, plus a short email from me.

Next step

Start with one product group.

We test the value on a real sizing question from your portfolio, within one week, with a small data package. If the POC doesn't convince you, it costs nothing.

Book a 30-minute call →