An AI Sales Agent for E-commerce Stores That Handles 700,000 Conversations a Month
Ruslan Leteyski rebuilt after Shopify killed their $8M ARR product overnight, and now runs Zipchat — one agent handling every customer conversation across every channel for merchants — at roughly $167K a month
Continue exploring this workflow
The Strategy
Ruslan Leteyski, based in Sofia, had built Checkout X to $8M ARR before Shopify changed its platform and ended the product overnight. Their response was Zipchat, an AI sales agent that sits between an e-commerce brand and its customers and handles the conversation on any channel — one agent, one configuration, every inbox merged into one place. The distinction they draw is between support deflection and selling. Zipchat is positioned as a sales agent rather than a support bot, which matters commercially: the same conversation that answers a sizing question is the one that decides whether an order happens. That framing is also why merchants pay for it, since a deflected ticket saves cost while a converted conversation makes money. The scale is what makes this more than a product listing. Zipchat handles roughly 700,000 conversations a month across its merchant base, at about $167K in monthly revenue and approaching $2M ARR, growing around 10% week over week. The stack underneath is deliberately boring — Ruby on Rails and Hotwire — which is a useful counterweight to the assumption that agent products require an exotic architecture. The part worth sitting with is the burn before it worked: roughly $20K a month for close to a year before reaching profitability. This is a founder who had already built and lost an eight-figure business, and it still took a year of funded losses to get the second one working.
How It Works
Pick a business where conversations directly cause revenue, so the agent's output is measurable in orders rather than tickets closed.
Position the agent as a sales agent rather than a support bot, since the commercial value sits in conversion rather than deflection.
Merge every customer channel into one place so a single agent configuration covers all of them instead of one bot per inbox.
Give the agent access to real store data — products, orders, policies — so it can resolve questions end to end rather than routing them.
Keep the underlying stack conventional; the agent behaviour is the product, not the framework.
Expect a long unprofitable stretch: roughly $20K a month of burn for close to a year before this one turned.
Sell into a platform ecosystem you already understand, but do not build so tightly on it that a platform change can end the business overnight.
Results
Ruslan Leteyski reports about $167K in monthly revenue and approaching $2M ARR, roughly 700,000 conversations handled monthly, and about 10% week-over-week growth, after nearly a year of burning around $20K a month before profitability. Figures are self-reported in an Indie Hackers interview and have not been independently verified.
Our Take
The reason this belongs here rather than in a tools roundup is the platform-risk story wrapped around it. Leteyski built an eight-figure business on Shopify's checkout and lost it when the platform moved; they are now building agents for the same merchants, and the lesson they carry is worth more than the ARR figure. The product framing is also instructive for anyone selling agent services: "support deflection" sells on cost and gets budget-cut, "sales agent" sells on revenue and does not. The honest caveat for anyone reading this as a template is the runway — nearly a year at roughly $20K a month of burn is not a bootstrapped path, and an operator without that cushion should not model against it. Best for anyone building conversational agents for e-commerce, or weighing whether to sell an agent as a cost saver or a revenue driver.
Frequently Asked Questions
The practical questions a builder or operator is likely to ask before trying a strategy like this.
What does this shopify stores customer service AI agent actually do?
This shopify stores customer service AI agent is a real workflow where the agent takes on an operational job, not just a brainstorming task. An AI Sales Agent for E-commerce Stores That Handles 700,000 Conversations a Month shows what that looks like in practice. Ruslan Leteyski rebuilt after Shopify killed their $8M ARR product overnight, and now runs Zipchat — one agent handling every customer conversation across every channel for merchants — at roughly $167K a month The practical value comes from the agent handling repeatable business work with enough autonomy that a human only steps in after context has already been gathered.
Who should use a shopify stores customer service AI agent like this?
This example is most relevant for shopify stores operators. It is especially relevant for businesses where speed to lead, after-hours coverage, or consistent intake quality directly affects revenue. The category here is Customer Service, which means the best fit is a team looking to turn a manual bottleneck into a repeatable system with a shopify stores customer service AI agent.
Which tools are used in this shopify stores customer service AI agent setup?
The source names Custom AI Agent, Stripe. That matters because one of the strongest signals in this directory is whether the operator shared the actual stack. Named tools make a shopify stores customer service AI agent strategy far more useful than vague claims about “an AI system” doing the work.
How hard is it to implement a shopify stores customer service AI agent like this?
Advanced difficulty is the current read. The listing suggests a launch window of months. Startup cost is listed as $200+/mo. We were able to extract 7 concrete workflow steps from the source. We would treat a shopify stores customer service AI agent like this as a workflow that needs real business context, testing, and exception handling rather than something you should copy blindly from one prompt.
What results can a shopify stores customer service AI agent produce?
Ruslan Leteyski reports about $167K in monthly revenue and approaching $2M ARR, roughly 700,000 conversations handled monthly, and about 10% week-over-week growth, after nearly a year of burning around $20K a month before profitability. Figures are self-reported in an Indie Hackers interview and have not been independently verified.
How credible is this shopify stores customer service AI agent case study?
Right now the evidence comes from an Indie Hackers post. That is enough for us to study and curate the workflow, but not enough on its own to treat this shopify stores customer service AI agent like an audited case study. We look for named tools, concrete results, and enough workflow detail to understand what was actually deployed, then we add our own editorial judgment on top.
Related Strategies
More AI agent strategies you might find useful
Building a $3,500 AI Customer Service Chatbot Live From Scratch
A full live build of a customer service chatbot with knowledge base retrieval, l…
A $40K MRR AI Customer Support Tool Built by Two Founders After a Failed VC Startup
Two founders pivoted from a failed VC backed startup to bootstrap an AI customer…
A $10K Healthcare Voice Agent That Handles Patient Intake and Appointment Booking
A voice AI agent for healthcare clinics that qualifies patients, verifies insura…
A Voice AI Receptionist for Veterinary Clinics That Books Appointments Automatically
A voice AI agent handles incoming calls at a vet clinic, checks calendar availab…
A Plumbing AI Receptionist That Books Emergency Calls and Logs Everything to a CRM
An AI voice receptionist for a plumbing company that books emergency service cal…
A Developer Built an AI Receptionist for Her Brother's Mechanic Shop to Recover 100+ Missed Calls a Week
A software engineer built a RAG-powered voice receptionist for her brother's lux…
Want more strategies like this?
Get weekly AI agent case studies in your inbox.