Case study

How Moliv answers 65%
of skincare questions with no human

Moliv is a Polish skincare manufacturer founded in Kraków by three scientists — a microbiologist, a biotechnologist and a quality expert. It was the first Polish brand to put live probiotic cultures into a face cream, and it sells direct from its own storefront in Polish, English and German.

3 min read

MOLIV Assistant
Type your question
Powered by spot

Languages

Polish · English · German

Integrations

WooCommerce

Before AskSpot

A patented formula, three scientists, and an office that closes at five

Moliv is not a brand anyone buys on a photograph. The creams carry live Lactobacillus plantarum cultures in a patented 3P formula — probiotics, prebiotics and postbiotics — worked out over two years in a laboratory by the three scientists who founded the company. That is the entire proposition, and it is also the entire problem: nobody buys it until somebody explains it.

The people who could explain it were the founders, and the desk in Kraków is open Monday to Friday, 09:00 to 17:00. The questions are not. They arrive at one in the morning and at eleven at night, in Polish, English and German, and they are rarely short — a shopper gives her age, her skin type and the retinal already in her evening routine before she asks anything at all. Answering each one properly was a consultation the team did not have the hours for.

Customer service desk

Mon–Fri, 09–17

Outside those hours

e-mail only

Expert advice came from

the founders

Questions that repeat most

ingredients & how to use

Rollout

How they rolled it out

One module, one storefront, and three things to get right before an agent can answer a skincare question properly: the catalogue, the science behind it, and the three languages it is sold in.

AI Chat Agent

Step 01

WooCommerce Catalogue Sync

Every product, and who it is for

A short catalogue, and that is exactly what makes it hard: four face creams that look nearly identical on a shelf, a repair serum, the oil-gel cleanser in two sizes, the TRY ME BOX of 2 ml testers and a body peeling. The WooCommerce store already files them by skin type, so the agent files them the same way.

What shoppers ask

  • What is the difference between the nourishing and the regenerating cream?
  • How long does one of the creams in the box last?
  • Which cream is best for mature skin?

AI Chat Agent

Step 02

Formula Knowledge Base

The science, and where it stops

The 3P formula, the live Lactobacillus plantarum cultures and their GRAS status went into the knowledge base so the agent can explain them in plain language. So did the limits: it does not hold the full INCI list and says so rather than guessing, and a pregnancy question goes back to the shopper’s own doctor, because Moliv has run no studies there.

What shoppers ask

  • Can I combine this cream with a copper peptide serum?
  • Can I use the nourishing cream while pregnant?
  • Can I put it straight on top of retinal?

AI Chat Agent

Step 03

Three Languages on One Storefront

Polish, English and German at the same address

molivcosmetics.com sells in all three languages from a single domain, so there is no market to route anyone to — the agent answers in whichever language the question arrived in. Polish is the bulk of it. The English and German conversations are a small, real share that nobody was ever on shift for.

What shoppers ask

  • Kannst du mir ein Peeling empfehlen?
  • Do you ship abroad?
  • Which cream for combination skin that keeps breaking out?

Measured in AskSpot

What the agent does in every conversation

65%

of chats resolved

3

shopper languages handled in chat

64%

of chats come in after hours

8 s

average first response

From real conversations

What Moliv shoppers actually ask

Three quarters of everything asked is a consultation: what is in it, how do I use it alongside what I already use, and which one is right for my skin. Shoppers write briefs, not queries — age, condition and the actives already in the routine, unprompted. And one question in four is about stock, because the brand's hero cream spent much of this window waiting on a raw material.

Ingredients & how to use38.2%
Skin-type advice36.6%
Stock & restock dates26.0%
Shipping & delivery8.1%
Asking for a human4.9%
Discounts & promotions4.1%
Orders & returns3.3%

About 8 messages per conversation · 64% arriving outside business hours · 8 s average first response.

More case studies

See how other stores use AskSpot

More stories from teams that automate support and grow sales with AskSpot.

All case studies

Morele.net

How Morele.net cut customer service costs by 90%

Morele.net cut support costs 90%, from 50 agents to 5. AskSpot resolves 65% of its 37,600 monthly chats with no human and answers Allegro questions too.

Read the story →

Militaria.pl

How Militaria resolves 72% of chats in 9 languages

Militaria.pl runs AskSpot across three domains in nine languages: 27% add-to-cart after a chat, 72% resolved with no human, 16,600 conversations a month.

Read the story →

4FIZJO

How 4FIZJO resolves 61% of customer chats with AI

AskSpot's AI Chat resolves 61% of 4FIZJO's 21,360 monthly chats with no human across 6 markets; its Inbox Agent auto-resolves 25% of email tickets.

Read the story →

Senetic

How Senetic turns 19.5% of technical IT chats into cart-adds

Senetic's AskSpot agent answers port, PoE and compatibility questions across seven European storefronts. 19.5% add to cart, 8.1% buy, 62% resolved by AI.

Read the story →

Konesso

How Konesso turns 1 in 5 chats into an order

Coffee is chosen by taste, machines by fit. Konesso's AskSpot agent does both: 21.6% of chats end in a purchase, 68% resolved, €47,600 of orders a month.

Read the story →

Mamabrum

How Mamabrum serves customers in 20 languages with one team

How Mamabrum reduced customer service inquiries by 30% and serves customers in 20 languages across 20+ EU storefronts with AskSpot — chat and email answered from one catalogue.

Read the story →

7case studies

See every story

Every merchant we have measured — what shoppers asked, what the agent did, and the numbers it moved.

Browse them all →

Test before you trust

Worried AI will cost you customers?

You never flip a switch and hope. Every answer is checked by our AI, our specialists and your own team before launch — and if you want extra reassurance, you can go live after hours first.

Layer 01

Self-testing AI

Every reply is checked automatically against your catalog and your rules, so off-topic or off-brand answers are caught before anyone sees them.

Layer 02

Vetted by experts

Our specialists challenge it with all kinds of questions, drawing on experience from dozens of e-commerce projects we've run, then sign off on the quality.

Layer 03

Tested on staging

Your own managers get a private staging environment to try the chat end to end — ask anything, push the hardest cases — and approve it before go-live.

Layer 04

After-hours launch

Want extra reassurance? Optionally go live only outside working hours at first, review every answer and the full statistics, then expand when you're ready.

You decide when — and if — AskSpot goes live.
No leap of faith, no lock-in.

Ready to make every conversation sell?

Book a demo and see AskSpot on your own catalog. Onboarding takes a few days.