
How Lévrard automates its incoming call management with voice AI
KEY FIGURES
80% of calls handled without an operator
Zero calls lost after hours
ROI within the first weeks
CHALLENGE
The Lévrard group receives a high volume of calls daily related to service requests. 80% of these calls come from individuals, and their processing follows a structured but time-consuming process: identifying the client, collecting information about the need, creating the client file and service request file, then scheduling an appointment taking into account distance, estimated intervention duration, and technician availability.
This process, however well-established, still relies heavily on human operators. The result: extended processing times during peak hours, internal resources tied up with repetitive, low-value tasks, and limited capacity due to customer relations center operating hours.
Prior to the project, several key challenges were identified:
- Absorb the volume of incoming calls without increasing headcount
- Reduce per-call processing time for standard requests
- Ensure 24/7 availability, including outside business hours
- Integrate the tool with existing systems without overhauling the IT infrastructure
- Ensure a seamless customer experience, with transfer to a human if necessary
SOLUTION
Qolaig designed and deployed an AI voice agent capable of handling incoming calls from individuals end-to-end, by integrating with the Lévrard group's internal APIs. The objective: to automate the processing of standard requests while preserving the quality of the customer experience and the option to transfer to a human operator at any time.
01. A voice agent that manages calls from A to Z
As soon as a call is received, the AI voice agent takes over: it identifies the client, collects information related to the service request, automatically creates the client file and service request file in the system, then proposes a suitable appointment slot. Scheduling relies on the group's internal APIs: technician availability, location, estimated duration, and rates to offer the right slot to the right technician, without human intervention. An integration with internal systems comparable to the one built at Adelya to connect an assistant to product data.
Examples of automatically processed cases:
- I need a technician for unclogging a drain.
- I'd like to receive an invoice.
- I have water damage, what is your availability?
02. Multilingual and available 24/7
The agent handles calls in multiple languages, expanding the group's capacity without additional training or recruitment. It operates outside business hours, ensuring no requests are lost at night or on weekends.
03. Human Transfer and Systematic Traceability
As soon as a request falls outside the standard scope (a complex situation, a dissatisfied customer, or a need for technical advice), the agent transfers the call to a human operator, with the context already collected. At the end of each call, a complete transcript and audio recording are automatically sent to a third-party API for archiving and quality monitoring.
RESULTS
- Zero lost calls outside business hours
- Real-time creation of customer and service records, directly within the IS
- Optimized scheduling based on technician availability, distance, and duration
- Multilingual deployment, without team training
RETURN ON INVESTMENT
For a group whose core business relies on field responsiveness, every poorly handled call is a lost appointment. By automating the processing of standard requests, Qolaig has freed up operators from repetitive tasks, allowing them to refocus on complex interventions and high-value customer relationships. With over 100 calls per day, automating 80% of the processing is equivalent to several full-time employees (FTEs) being redirected to tasks with a direct impact on customer satisfaction and revenue. The solution becomes self-financing within the first few weeks of operation. A logic similar to that of Dana Avocats, which automated its answers to recurring requests.
FAQ
How much does an AI workshop with Qolaig cost?
The AI workshop costs €5,000 excl. VAT for one day on site. 50% of this amount is deducted from development fees if the project moves forward.
How long does it take to deploy a solution?
The first use cases are usually live 2 to 6 weeks after the workshop.
Is our data kept confidential?
Yes. It is never used to train third-party models and stays in your environment, with hosting suited to your GDPR requirements.
What did Qolaig deploy for the Lévrard group?
An AI voice agent that handles incoming calls from individuals, from identifying the client to booking the appointment.
What happens with a complex request?
The agent transfers the call to a human operator, with the context already collected.
What share of calls is handled automatically?
80% of calls are handled without an operator, including at night and at weekends.

%20(1).webp)



















.webp)



%20(1)%20(1).webp)

.webp)




