Thulium integration
AI inbox agent for Thulium
Reads, categorises and answers tickets inside Thulium — on the queue you choose, and never before you switch it on.
What you get
- Repetitive tickets answered without a human
- Order and delivery questions resolved from your store data
- Replies in the customer’s language, on every market you serve
- Consistent answers on returns, shipping and policies
- Overnight and weekend volume handled before your team logs in
- Escalation to your team the moment it should happen
Requirements
It plugs into the helpdesk you already run
Connection
API key
Code to write
None
Agents
One per market
own name, language and knowledge
Rollout
Test, draft, live
- Web forms
- Chat
- Phone
- Multi-queue
- Multi-market
How the connection is built
Three layers, and you draw the boundary
No forwarding rules and no mailbox migration. The agent works inside Thulium, on the tickets you hand it.
01
API connection
Your Thulium instance and an API key, entered once in the AskSpot panel. Nothing is installed on your side and no code is written. Run several agents if you sell in several markets — each with its own name, language and knowledge base.
Required
02
The queue it owns
Choose the queues, ticket statuses and channels the agent works on. Everything outside that selection stays with your team, untouched — the agent never sees it.
Required
03
Store and order access
Connect your catalog and orders and the agent resolves “where is my parcel?” instead of routing it to a person. Start read-only and extend the permissions when you’re ready for it to act on orders — the two layers above already work without this one.
Optional
Scope and control
You draw the line, ticket by ticket
What it picks up
- Queues you choose
- Ticket statuses you choose
- Channels you choose
- A separate agent per market
What it never touches
- Senders and whole domains you exclude
- Subjects you exclude — legal, complaints, press
- Anything outside the queue you chose
- Anything at all, while test mode is on
See it working in your inbox
Book a demo and we’ll run the agent on your own queue, in test mode, before anything is sent.
Going live
Nothing reaches a customer until you say so
Three modes, switched from the panel. Most teams spend a week in each before moving on — and you can step back at any time.
Mode 01
Test mode
The agent works through real tickets and writes real answers. None of them are sent. You read what it would have said and decide whether you trust it.
Mode 02
Draft mode
Answers are prepared as drafts inside Thulium. Your agent reads each one and decides whether to send it, edit it first, or write their own. The customer only ever sees what a human approved.
Mode 03
Responder on
The agent replies on its own, inside the queue you defined and nowhere else. One toggle takes you back to drafts if you want a closer look again.
You decide when — and if — AskSpot goes live.
No leap of faith, no lock-in.
Security and control you can trust
AskSpot is designed to operate safely in demanding e-commerce — with data protection, reliable AI and full operational control.
Case studies
Real results for e-commerce stores
See how online retailers use AskSpot to automate conversations, reduce support workload and grow sales.
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 →
How Sportano handles 12,750 conversations a month with one agent
Sportano's AskSpot agent covers the whole order lifecycle — specs and restock questions before the sale, cancellations and returns after it. 71% of chats resolved with no human, 17% add to cart, across Polish and German storefronts.
Read the story →
How Nutridome resolves 86% of chats with no human
Nutridome's AskSpot chat agent resolves 86% of conversations with no human across four storefronts, and answers order questions on the tracking page itself. 2,200 conversations a month on chat and the Thulium email queue.
Read the story →
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 →
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 →
How Sport-Shop turns 17% of chats into cart-adds
Sport-Shop.pl's AskSpot chat agent puts an item in the basket in 17% of conversations and resolves 88% with no human — delivery timing, sizing and fit for camping, beach and garden gear. 15,800 conversations a month across chat and email.
Read the story →
See every story
Every merchant we have measured — what shoppers asked, what the agent did, and the numbers it moved.
Browse them all →
Testimonials
What our customers say
Reviews from e-commerce companies that automate support and improve customer experience with AskSpot.
“AskSpot enables us to provide superior support for Ariston customers at every stage — from pre-purchase advice to post-sale and service assistance. Equally important, Ariston benefits from the valuable insights AskSpot delivers about customer preferences, which help us continuously improve the customer experience.”
“We have been impressed by how AskSpot delivers a seamless experience for our customers while remaining incredibly intuitive for our own team to manage.
Beyond the ease of use, the detailed analytics and reports are of enormous value — they help us make better decisions around customer satisfaction. Behind AskSpot stands a team that puts innovation first and keeps developing the product to match changing business needs.”
“AskSpot is a revolutionary solution for us. We provide our customers with the key information they need instantly while simultaneously reducing the workload of customer service.”
“AskSpot has significantly improved customer service in our stores. The assistant not only searches the product catalog and helps customers choose the right items, but also automatically checks the status of orders and complaints — relieving the team and shortening response times.
The greatest value for us is the scalability of the solution and the ease of integration with additional stores and markets. We treat AskSpot as a strategic component of our customer experience development and sales automation.”
“AskSpot has genuinely improved our customer service — customers get answers faster, and the team handles fewer repetitive tickets.”
“Great collaboration and excellent business results. Most importantly, our customers enjoy using AskSpot because of its accurate and quick responses.”
See every testimonial
Read what the e-commerce teams who put AskSpot live say about working with it.
Check all the testimonials →
Before you connect
The questions a support lead asks first
Everything worth settling before an AI agent goes anywhere near your customers.
Will it email our customers without us seeing it first?
Not unless you decide it should. The agent starts in test mode, where it writes answers that are never sent. Draft mode is the middle step: it prepares replies inside Thulium and your team chooses whether to send, edit or discard each one. Only when you switch the responder on does it reply by itself.
Which tickets does it actually touch?
Only the queues, statuses and channels you select. You can also exclude individual senders, whole domains, and any subject line you’d rather it left alone. Everything else stays with your team.
What can it do with orders?
Whatever you grant it, and nothing more. Most teams start read-only, so the agent can look an order up but never change it. When you’re ready, you can extend the permissions to let it act — cancel, edit or start a return — scoped to exactly the operations you approve.
Does it work across our markets?
Yes. Run a separate agent per market, each with its own name, language and knowledge base, all reporting into the same panel. Customers are answered in the language they wrote in.
How fresh is the product data it answers from?
The product feed is re-read automatically once every 24 hours. Our support team can trigger a re-sync on request when you’ve made a large change, and higher plans run the sync more frequently.
Where does our data live?
Inside the EU, and never used to train external AI models. Deleted on request. More on security →
What if we want it gone?
Switch the responder off and revoke the API key. Your tickets, history and workflows stay exactly where they are — they never left Thulium.