We have long been actively developing AI capabilities on the Rubus platform. This past summer we built a new feature which is now being tested by several of our clients.
The new feature is an AI assistant for communication with homebuyers. It is designed to simplify and streamline case handling and warranty claims in the aftermarket phase, while enhancing response quality. The goal is to help your customer service team craft clear, professional and neutral replies. Watch this video to learn more
The AI engine uses the dialogue with the homebuyer as its basis and suggests a response. Think of it as an embedded ChatGPT right within Rubus Warranty Handling. The AI engine does not provide legal advice and does not reference laws or regulations.
Benefits reported by test users
“Because the AI assistant is built into Rubus, I don’t have to leave the platform to get help”
“It was very easy and intuitive to start using, especially since I’ve already used chatGPT for some time”
“I save time because the AI assistant suggests responses based on case details and message history. It also improves the quality of communication”
“The AI assistant handles the simple, routine replies, allowing us to focus on the more complex cases”
“I always feel in full control. The feature suggests responses, and experienced case handlers review and send the final reply”
“The solution supports multiple languages. It is easy to translate back and forth”
“The AI assistant can quickly summarize long dialogues and multiple messages, which saves a lot of time”
Common questions from clients
Do data sent to or received from the AI engine leave the EU, particularly with respect to GDPR?
No. We use Amazon Web Services (AWS) Bedrock with data centers in the EU. AWS is already an approved provider in our Privacy Policy and Data Processing Agreement.
When I send prompts to the AI engine, is my text stored?
No. AWS Bedrock does not store the prompts you send.
When I receive a response from the AI engine, is it stored anywhere?
No. AWS Bedrock does not store the responses it generates.
Is data used to train models?
No. AWS Bedrock does not use customer data to train models. You can read more in AWS Bedrock’s documentation: “Amazon Bedrock doesn’t store or log your prompts and completions. Amazon Bedrock doesn’t use your prompts and completions to train any AWS models and doesn’t distribute them to third parties.”
We continuously work to simplify processes and make your daily work easier by leveraging AI where it makes sense. Many more smart features are already in development. If you’d like to test this feature or have any questions about the solution, please reach out to our team.
