Case study

How Ogrodosfera turns garden questions
into €384,000 a month

Ogrodosfera.pl is a Polish garden and outdoor retailer selling pergolas, pavilions, carports and sheds, garden furniture and parasols, greenhouses and children's play equipment, including its own Garden Point brand. Across the rest of Europe it trades as GardenWay.

4 min read

Ogrodosfera Assistant
Type your question
Powered by spot

Markets

9 storefronts: PL · HU · SK · RO · NL · DE · CZ · BG · LT

Years on market

15

Results

Key results

Measured in AskSpot across 19,207 chats over a 60-day window at the peak of the garden season. The average chat-driven order is €455, because what gets bought is a pergola, a pavilion or a full furniture set, not an accessory.

€384,000

in chat-driven orders a month

15%

of chats fill a basket

9%

of chats end in a purchase

90%

of chats resolved with no human

Before AskSpot

The season is three months long

Garden retail has a season, and the season is short. Ogrodosfera does the bulk of its year between May and July, and in those weeks a shopper standing in front of a €350 pavilion wants to know things the product page cannot tell them: whether the roof will hold a winter, what the seat height is, whether a 3 × 4 m frame will actually stand on a 320 × 385 deck, whether the side curtains and the mosquito nets are included or extra.

Those are showroom questions about a showroom purchase, and two thirds of them arrive after the office has closed — in the evening, at the weekend, in the middle of the only quarter that matters, in nine languages across nine storefronts. Staffing that is less a scheduling problem than an arithmetic one, and an unanswered “will it fit?” is not a delayed sale. It is a shopper who closes the tab.

What decides the sale

specifications

Typical basket

one large item

Storefronts to staff

9 languages

Help after closing

none

Rollout

How they rolled it out

One module, three jobs, added in the order the catalogue demanded them: answer the spec, then match the part, then do both in eight more languages.

AI Sales Agent

Step 01

Catalogue & Spec Grounding

Answering from the product data

Over ten thousand products were indexed on the numbers that decide a garden purchase — post spacing, seat height, sheet gauge, roof weight, snow and wind rating — so the agent quotes the specification instead of paraphrasing the description.

What shoppers ask

  • Is this gazebo an all-year one?
  • How thick is the sheet metal on this shed, and will it take wind?
  • What’s the seat height?

AI Sales Agent

Step 02

Accessory & Spare-Part Matching

The second sale, and the one that keeps a customer

Side curtains, mosquito nets, replacement canopies and ground anchors were mapped to the frames they fit, so “I have a Valencia 3×4” returns the right part rather than a category page. It is 13% of every conversation.

What shoppers ask

  • Can I buy just the roof cover?
  • I need a new curtain or blind for a 3×4 La Palma pergola
  • Can I add a brown canopy and cushions to the Valencia swing?

AI Sales Agent

Step 03

Nine Storefronts, One Catalogue

GardenWay, in the shopper’s own language

Separate agents run on ogrodosfera.pl and the eight GardenWay domains — Hungarian, Slovak, Romanian, Dutch, German, Czech, Bulgarian and Lithuanian — off the same product data. Hungary alone is 16% of all chat.

What shoppers ask

  • Mikor lesz elérhető ez a garnitúra? — Hungarian
  • Aká je dĺžka sedačky aj s tým dreveným priestorom? — Slovak
  • Vine husa de acoperiș cu accesoriile de montaj? — Romanian

Measured in AskSpot

What the agent does in a month

43%

product recommendation click-through

9,600

conversations handled a month

66%

of chats come in after hours

9

markets, in the shopper's language

From real conversations

What Ogrodosfera shoppers actually ask

Two topics are two thirds of everything asked, and neither of them is about an order. "What exactly are the dimensions, and will it survive a winter?" comes first; "which of these should I buy?" comes a close second. Accessories are the quiet third — a frame outlives its canopy, and the shopper who needs a new one knows the model but not the part.

Product specs & features33.3%
Finding the right product31.2%
Delivery & buying terms13.9%
Accessories & spare parts13.3%
Discounts & promotions4.7%
Availability & restock3.9%
Returns & complaints3.7%
Fit & compatibility3.5%
Order status & changes3.1%

Based on 19,206 tagged conversations over 60 days · about 8 messages each · 66% arriving outside business hours.

More case studies

See how other stores use AskSpot

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

All case studies

Focus Garden

How Focus Garden books €102,600 a month in chat-driven orders

Focus Garden's AskSpot agent answers pergola size, durability and delivery — €102,600/mo in chat orders, €622 average, 80% resolved with no human.

Read the story →

Morele.net

How Morele.net cut customer service costs by 90%

Morele.net cut customer service costs by 90% and went from 50 support agents to 5. AskSpot resolves 71% of its 37,600 monthly chats with no human, and answers Allegro marketplace questions from the same catalog.

Read the story →

Militaria.pl

How Militaria resolves 83% of chats in 9 languages

Militaria.pl runs AskSpot AI chat across three domains in nine shopper languages: 48% product recommendation click-through, 27% add-to-cart after a chat and 83% of chats resolved with no human — 16,600 conversations a month, over half after hours.

Read the story →

4FIZJO

How 4FIZJO automated 50% of customer inquiries with AI

4FIZJO cut website calls and messages by 40% and automates a third of its helpdesk tickets. AskSpot's AI Chat resolves 74% of its 21,360 monthly chats with no human, across 6 markets, and its Inbox Agent clears email and Allegro tickets in Thulium.

Read the story →

Tatuum

How Tatuum turns 18% of fashion chats into a sale

Tatuum's AskSpot sales agent turns 18% of chats into a purchase and 28% into cart-adds — reading the size chart from real body measurements, in Polish and Hungarian. Its inbox agent auto-resolves 41% of post-sale emails.

Read the story →

Twoje Meble

How Twoje Meble fills 1 in 5 furniture carts

Twoje Meble's AI sales agent adds an item to the cart in 18.5% of chats and resolves 88% with no human — 2,057 furniture conversations a month, 41% of them after the showroom closes.

Read the story →

25case 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.