How Experian improved agent response times under 3 seconds with Snorkel Evaluate
Improvement in Net Promoter Score
Second agent response time

Challenge
Experian’s customer support team used to require agents to manually find and customize templates to respond to common questions. Leadership recognized an opportunity to improve response times and customer experience by using an LLM system to automatically handle a significant portion of support emails—enabling human agents to focus on more complex requests.
Solution
Experian deployed an Agentic AI solution built on AWS to automate and accelerate customer service. The AI system first redacts PII from the incoming emails and classifies them to ensure they are appropriate to answer. It then uses a version of Meta’s Llama3-8b, fine-tuned with data curated through Snorkel, to generate replies. The system queries the model multiple times with different functional modalities to generate a final draft. A human agent then reviews the message, edits as necessary, and sends the completed message.
Outcomes
Experian has reduced costs and response times while improving customer satisfaction. A survey found that the project boosted Experian’s Net Promoter Score by 8% while delivering responses in less than three seconds.
Ready to get started?
Take the next step and see how you can accelerate AI development by 100x.