TREN

E-commerce · Scope to be defined during discovery

AI System for Extracting Product Fields from Supplier Catalogues

We design an AI system that reviews supplier PDFs, tables and product sheets together with source and freshness information. The system prepares product fields linked to their source locations but does not treat them as final decisions. If units conflict or a table cannot be read, the suggestion is not put into effect; the product data specialist makes the final assessment.

Representative product data operations panel with a work queue, checks and an audit trail: supplier field extraction queue — **Supplier field extraction queue** Representative interface — contains no real data. Supplier names are coded. The panel does not select final fields or create product records.

The problem

In day-to-day operations, supplier PDFs, tables and product sheets arrive in separate records and files, preventing the team from reviewing the same case in one place.

As a result, the link to the source can be lost while source-located product fields are prepared, leading to repeated checks and uncertainty about the basis for the decision.

Incomplete automation may overlook conflicting units or unreadable tables, while poorly controlled automation creates a risk of recording incorrect measurements.

What we set out to improve

Time taken for the draft source-located product fields to be ready for review
Accurate routing of records with conflicting units or unreadable tables to the correct specialist queue
Recording of suggestions amended or rejected by the product data specialist

How the system works

01 Retrieve supplier PDF, table and product-sheet data from an approved source
02 Verify the source system, record identifier and freshness information
03 Transform the fields into the target process schema
04 Prepare draft product fields linked to their source locations
05 Compare the draft with business rules and source records
06 Exception check: units conflict or a table cannot be read
07 Product data specialist approval, amendment or rejection
08 Write the input, suggestion, amendment and final decision to the audit log

Methods we used

Source-traceable data extraction for supplier PDFs, tables and product sheets
Structured output that restricts source-located product fields through business rules
An exception gate that separates records with conflicting units or unreadable tables
A queue that shows the source and suggestion together for the product data specialist
Duplicate-processing and rollback records to manage the risk of recording incorrect measurements

Where people stay involved

The product data specialist is the final decision-maker. If units conflict or a table cannot be read, the workflow stops and the case is presented to the specialist with the supporting records. The specialist can amend or reject the suggestion, or stop the process.

Data and security

Only the fields required for the task are processed from the supplier PDFs, tables and product sheets. Source-system permissions are preserved, and personal and commercially sensitive data is minimised before being passed to the model. Every read, suggestion, human amendment and write to the target system is logged.

Who this suits

A good fit

Teams carrying out repetitive reviews in e-commerce
Companies with defined ownership for sources and approvals
Organisations that want exceptions to remain under human oversight

Not a good fit

When source data is not current
When no decision owner or rollback process has been defined
When the existing method is sufficient for the low volume involved

Frequently asked questions

What data is used?

Supplier PDFs, tables and product sheets are used. The exact connections, fields and retention limits are defined during the access review.

How are exceptions handled?

If units conflict or a table cannot be read, the workflow stops. The record enters the product data specialist's queue with source evidence.

How is poorly controlled automation limited?

Because incorrect measurements could be recorded, no final action is taken without human approval. The source, suggestion and human decision are recorded separately.

Project led by:DijitalPi

✦ PI ASSISTANT · ARTIFICIAL INTELLIGENCE

online

Ask the DijitalPi AI Assistant your question

No need to fill in a form and wait for a reply — write your question and let Pi, trained on DijitalPi's 20 years of know-how, answer within seconds.

Instant answers, 24/7
Service-specific context — no generic replies
Can connect you to a free consultation if you wish

Hi! 👋 I'm Pi — DijitalPi's AI assistant. Write whatever you'd like to know about AI System for Extracting Product Fields from Supplier Catalogues and I'll answer right away.

Pi Assistant answers are for information purposes; for a proposal get in touch.

ASK AI ABOUT DIJITALPI

Let an AI explain what DijitalPi does.

Opens your chosen assistant with a ready research prompt. It reads the site live and answers.

ChatGPT Claude Gemini Grok Perplexity