E-commerce

Returns, support and product data, handled consistently

Returns, catalogue work and customer questions grow with your revenue. We automate the volume and apply your policy the same way every time, so you don’t need a bigger team.

Problems you’ll recognise

What grows with every order

Returns that grow with revenue

At a 15% return rate, every €1M in sales brings more than 1,500 returns. Checking condition, applying policy and issuing refunds by hand becomes a department of its own.

Average online return rate: 14–17% of sales (NRF 2024 data).

Slow refunds that cost repeat purchases

Most shoppers check the returns policy before they buy (67%, according to NRF). A slow answer erodes trust even when it is the right one.

Fraud and chargebacks

In a manual queue, the customer with 7 returns in 60 days doesn’t stand out. Automated checks flag the pattern before the refund goes out.

What we built for an e-commerce client

800 returns a week, handled by one person instead of four

Customer support · E-commerce

Before: An online fashion retailer handled 800+ returns a week with four full-time staff, slow resolutions, inconsistent policy calls and no view of fraud.
What we built: A returns system that checks item condition from photos, applies the policy automatically, flags possible fraud and sends only genuine edge cases to a person.
Result: One person now does what four used to, and every return gets the same policy decision.

4 days → 6 hours to resolve a return

Saved per year€155K

Show the calculation

3 FTEs reallocated (€38K × 3 = €114K) + estimated fraud/chargeback reduction (€41K). Payback: about 10 weeks.

Read the full case

The service behind it

What the returns system does

This is our customer support service, set up for returns. People still make the hard calls, and the system takes the routine ones.

Reads the customer’s photos and judges condition (unused, worn, damaged, missing tags) against your policy, logging each decision.
Turns your policy into rules you can change yourself: refund, exchange, store credit or reject, applied the same way every time.
Flags frequent returners, inconsistent claims and mismatched details before the refund runs.
Sends genuine edge cases to one reviewer with the images, history and policy reasoning attached.

Technical details

GPT-4 Vision

Judges item condition from photos

Python / FastAPI

Runs returns intake and the policy engine

LangChain

Walks each return through your policy

Redis

Keeps the queue and statuses live

PostgreSQL

Stores returns history and the audit log

React (exceptions UI)

Where your reviewer sees each case

Free 30-minute call

How many returns do you process a week?

Share your returns volume, your team and your main bottleneck. We’ll map what can be automated, what needs a person, and what the payback looks like.

“You talk to me, the engineer who builds your system. If AI isn’t the right fix for your problem, I’ll tell you.” Ayman Santeer, Founder

Book a free call

Prefer email or phone?

contact@elanova.ai +31 6 40747312 WhatsApp