Contact
Bolt Energie

Transforming Bolt’s customer service with a Large Language Model

Bolt-logo
TagsCustomer ServiceEnergy
Bolt-logo
TagsCustomer ServiceEnergy

Bolt Energie, Belgium’s first platform connecting consumers directly to local green energy producers, turned to ML6 to enhance customer service. Together, they built an AI solution that streamlines ticket handling and improves support quality.

Find out more
bolt_Engineers walking on factory roof inspect survey and check solar cell panel by hold equipment box ,s By APchannel_envato

Catch up quickly

ML6 built an AI solution for Bolt Energie that automatically detects the language and category of customer service tickets, with 80% of tickets now routed correctly. This saves agents up to four days per week in sorting time, letting them focus on real customer interactions. Using Retrieval-Augmented Generation (RAG) on AWS, the system also generates answer suggestions from Bolt’s internal knowledge base, boosting efficiency while ensuring accuracy and relevance.

Continue reading

About this client

Bolt Energie is the first Belgian energy platform that makes a direct connection between energy generators and consumers by supplying green electricity and natural gas. The customer chooses from which local producer he purchases green energy: from a farmer from Zulte to floating hydroelectric power stations on the Maas.

Impact

With the AI solution built by ML6, customer service agents now have an accurate indicator for the language and category of an incoming customer service ticket. This enables the agents to focus on what’s really important, instead of sorting the tickets first, resulting in a time and efficiency gain.

smart energy

Challenge

Customer care is a significant and important workload at Bolt Energie. As Bolt grows, the need for customer care grows as well. With Generative AI (Large Language Model), the way of offering customer support can be tremendously improved, which results in lower costs for each request and the opportunity to do even better customer care with the same team size.

ML6 provided us with a fast solution to bring the workload on our customer care significantly down. Communication was clear from the start & they ensured a smooth handover.
Jasper Verschuere
Mirko RorerDevelopment Manager, Bolt Energie

Solution

To reduce the growing workload on customer care, Bolt Energie partnered with ML6 to build an AI-powered system that classifies tickets, detects language, and generates more accurate answers. By combining Large Language Models with Retrieval-Augmented Generation (RAG) and deploying on AWS, the solution streamlines support while staying cost-efficient and reliable.

ML6 BESS systems
  • Smart Ticket Classification

    Large Language Models automatically assign categories to incoming customer questions, removing the need for labeled datasets or custom task-specific training.

  • Language Detection

    An open-source model identifies the language of each ticket, ensuring accurate routing to the right support team.

  • Domain-Specific Answers with RAG

    General AI answers weren’t precise enough, so ML6 integrated Retrieval-Augmented Generation to give the model access to Bolt Energie’s internal knowledge base for more relevant responses.

  • Scalable Cloud Infrastructure

    Built on AWS with services like OpenSearch and Bedrock, the solution leverages managed LLMs to avoid the high costs of self-hosting while ensuring scalability and reliability.

Results

The AI-powered solution brought measurable efficiency gains for Bolt Energie’s customer care team, cutting manual work and boosting agent productivity.

80%

of tickets auto-assigned correctly

4Days

saved per week in manual sorting

3X

agents reply quicker with AI-generated suggestions

Share this on:
Benjamin Praats 1-1
Benjamin PraatsClient Executive, ML6

Inspired?
Let’s connect and make it happen!

Ready to elevate your AI game? Schedule a meeting with us today and let’s craft a winning strategy together!

Let's schedule a talk
Benjamin Praats 1-1
Benjamin PraatsClient Executive, ML6

What others also liked

Cupcake ipsum dolor sit amet apple pie.

Frequently Asked Questions