Skip to main content

How ChatGPT Enhances Customer Service

PoC for increased momentum in a mobility company: Our agent assist solution boosts knowledge and efficiency

#customerservice #ChatGPT #efficiency

Our Impact

  • PoC for the ChatGPT-based agent assist solution in 4 months

  • Integration of various internal knowledge databases

  • Connection to internal infrastructure and the conversational AI platform

The Challenge

The mobility company handles several million phone inquiries annually in its customer service center. The call center agents often receive only brief training and face the challenge of answering questions about a complex product portfolio.

Together with the client, we set an ambitious goal: to reduce call duration by 10 percent, increase the first-call resolution rate by 10 percent, and significantly improve customer and employee satisfaction. The solution is based on ChatGPT to assess whether the use of this technology in customer service is technologically, economically, and qualitatively viable.

The Solution

We developed a proof of concept (PoC) that makes the client's various knowledge sources searchable using ChatGPT within a MRKL approach (Modular Reasoning, Knowledge, and Language). In this setup, ChatGPT acts as a kind of router, retrieving information from one or more knowledge sources depending on the query. The system's output includes a summary of the search results that answers the original question, while also citing the underlying information sources.

For employees, this can mean significant time savings. Typically, they have access to multiple internal knowledge databases, but searching through them during a call can be cumbersome, time-consuming, and costly.

To quantitatively evaluate the solution, we developed a framework around it. This framework allows us to vary different parameters, such as those in the areas of word embeddings and prompt engineering. Responses are generated for each parameter set and then compared by ChatGPT with answers previously marked as correct. This process is iterated multiple times to fine-tune the parameters for optimal answer quality.


Let's talk AI


More AI