Customer: Large Online Retail

Florium is the largest online plant and gardening retailer in Ukraine. The company offers a wide assortment of more than 5,000 plant varieties, selling planting materials across Ukraine and abroad. According to the latest publicly available figures from open sources (including Forbes rankings), Florium reported revenue of approximately USD 5 million in 2022. The leadership places strong emphasis on high-quality customer service, timely communication, and maintaining loyal relationships with returning customers to support stable and controllable demand.

Challenge: Reduce returns and increase sales through upselling

During peak periods, the Florium team struggled to personally reach every customer who had placed an order in a timely manner. For example, on Black Friday alone, the company made 2,000 outbound calls, with an average length of 60–70 seconds each. By transferring this process to an AI agent created by EVE.Calls, the company saves approximately 36 hours of human labor.

As noted by Florium’s manager, customers are typically not responsive to SMS notifications, which leads to higher order return rates for various customer-related reasons, such as impulsive purchases or changes of address. As a result, confirmation calls are essential.

Customer loyalty is especially critical because the business relies heavily on repeat customers who regularly purchase planting materials and seeds over multiple seasons. This dependency requires timely communication and a reliable buying experience. If customers do not receive enough support, it directly affects their willingness to place future orders, making operational delays a risk not only to short-term sales but also to long-term customer retention.

Solution: AI Telephony for Order Confirmation and Upselling

EVE.Calls built an AI Voice Agent for outgoing order-confirmation calls, designed to handle high-volume seasons without overloading the call center. The AI Agent performs a full sequence of actions that previously required several minutes of a manager’s time. The conversational AI:

• greets the customer politely and introduces itself as Florium’s assistant,
• states the expected delivery timeframe and confirms the order price,
• asks whether the customer wants to modify the order, 
• offers a relevant upsell item,
• adapts its dialogue depending on the customer's reaction
  
  

This AI agent includes more than 20 tailored responses that enable the AI to interpret customer intent with high accuracy. Whether the customer accepts the upsell, asks questions, or politely declines, the agent continues naturally until the order is fully confirmed.

Conversation Example: 

Transcript:

- Hello.

- Hello! My name is Anastasia, I am the voice assistant of Florium — a reliable online store of garden and decorative plants. We truly appreciate that you chose our shop. I’m calling to confirm and finalize your order, which was placed for the amount of 50 USD. The estimated shipping time is December. On the day of dispatch, you will receive an SMS with the tracking number. Do you have any questions, or would you like to make any changes?

- No, everything is fine.

- I would also like to recommend adding our promotional item to your order — a tulip mix called “Assorti.” They look very beautiful, and there are 5 bulbs in each pack. The discount is 50%, so the price is only 2 USD. Shall I add it to your order?

- Yes, okay.

- How many packs would you like to add?

- One.

- Got it. If you have any questions, please feel free to call us — we’ll be happy to help. We look forward to your future orders. Have a wonderful day!

- All the best!

- Thank you!

Advantages of the AI Voice Agent

• Significant reduction in call center load: 36 hours of human labor saved across 2,000 calls during the Black Friday 2025 season.
• Faster order confirmation = fewer cancellations and complaints: 90% of customers confirmed their orders with the AI agent, without cancellations or returns.
• High level of engagement: 60% of customers stayed engaged throughout the entire call, with no early drop-offs, including during the upsell segment.
• Automatic revenue generation: more than 10% of calls resulted in an additional item being added to the customer’s order.

Results

To evaluate the effectiveness of the conversational AI communication, EVE.Calls applied its proprietary evaluation methodology. During the pilot phase, EVE.Calls reviewed and analyzed all call recordings involving the AI Voice Agent. Following customer approval, the AI Voice Agent was deployed in live operations. From approximately 1,000 outbound calls processed across multiple successful campaigns, a representative 10% sample was selected for in-depth qualitative analysis.

Using this methodology, the selected calls were assessed across various dimensions, including logical consistency of the dialogue, relevance of responses, response latency, accuracy of personal data recognition provided by the client, and tone of communication. Based on this analysis, the AI Voice Agent demonstrated over 97% accuracy in managing conversations.

In the remaining cases (3%), minor non-critical issues were observed, such as brief response delays or occasional conversational imperfections. These did not result in incorrect information, policy violations, data exposure, or any negative impact on clients. All such issues are being addressed through ongoing system improvements.

Overall, EVE.Calls’ solution supported a significant increase in upselling and a reduction in manager workload during peak periods, enabling faster order processing.