Meet Heidi: Heidelberg Materials’ new AI voice agent supporting order management

• In a pilot project in Australia, Heidelberg Materials is testing Heidi, an artificial intelligence (AI) voice agent that assists in managing order requests. Heidi communicates in natural language, works with SAP in the background, and hands calls over to customer service agents when needed. 

We spoke with Nimit Kamdar, Global Program Lead for AI in Customer Service, about why the company introduced Heidi, how the pilot works, and what the teams learned so far.

Why did you start exploring AI for customer service?

We believe that delivering an exceptional customer experience requires creating a connected and intuitive journey that gives customers real choice in how they engage with us. Introducing the AI voice agent for customer service centre is an important step in advancing this experience as part of our broader omnichannel strategy. Our goal is to expand customers’ options, whether they prefer digital, phone or personal interaction, while ensuring that every touchpoint feels seamless, consistent, and relevant. In this way, Heidi strengthens our focus on customer excellence, which in turn drives a more flexible and customer-centric experience. 

Which part of the customer journey does Heidi support?

The focus is on order management. Customers can choose to wait for a customer service agent or immediately speak with Heidi by pressing 1️⃣. Heidi can retrieve the customer’s orders, identify the project and delivery details, and execute changes in SAP.  

If Heidi cannot complete the task or the customer wants to speak to a customer service agent, the call is handed over seamlessly with a summary of the conversation, so the customer does not have to start the conversation from scratch. This eliminates one of the most common sources of frustration in such processes: being passed from an AI to a customer service agent and having to repeat the same information all over again.

What is customer feedback like?

The pilot started with around 35 customers. Now, about 500 callers from 250 customers have access to Heidi. Since this type of service is new in our industry, customers were curious how it would sound and behave.

They appreciate that the voice is natural and dialogues are flexible, unlike traditional Interactive Voice Response (IVR) systems. Also, it helps them skip the queue during peak times, with quick and smooth handovers to humans, when needed.

Today, the reliability of intent recognition and order identification is above 90% and increases as we refine the system. Not all customers want to speak with AI, but many appreciate not having to wait.

What is the technical setup behind Heidi?

Heidi is technically orchestrated across multiple systems which handle telephony, conversation logic, and business processes. Within the conversation flow, we leverage a mix of generative AI and deterministic logic. The AI can speak naturally, but the order-management steps follow a controlled sequence to avoid mistakes.

Who is involved and how is the project built?

Australia was selected for the pilot due to its highly structured ready-mixed concrete processes, strong local accountability, and committed executive sponsorship. This is essential: without local commitment and well-organised processes, even the best AI solution cannot succeed. 

We work in a collaborative cross-functional set up that brings together a lean core team of experts, strongly supported by our internal digital teams, our technology partner, and, importantly, dedicated local project management working in close alignment with highly engaged teams in Australia. 

Their ongoing commitment and alignment provide the stability and focus required to deliver a high-quality outcome. At the heart of our work is a simple principle: we genuinely care about customer experience and are committed to making Heidi a success. 

You also work on AI for email processing in Europe. What does that look like?

Processing customer emails is time consuming, especially when the information given is incomplete. AI now reads these emails, extracts the fields needed to create an order, and creates the order in SAP. For incomplete emails, AI asks the customer to clarify missing information. This significantly reduces manual workload. We also ensure that a human is always involved for oversight.

Could Heidi become a chatbot?

Yes. Since all logic is text-based, converting the voice agent into a chat agent channel would require almost no redevelopment. 

What are the next steps for Heidi?

We are strengthening the solution in Australia by adding targeted features that enhance the customer experience and automate additional steps, preparing Heidi for thoughtful global scaling grounded in customer needs and business value.