Image

Experian improved agent response times under 3 seconds with Snorkel

Impact
1-3

Second agent response time

35%

of customer email responses now automated

8%

Improvement in Net Promoter Score

The 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.

The 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.

The outcome

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.

Image
Share this customer story

More customer stories

View all stories
Image
From hours to seconds on CLO contract review with 94% end user acceptance
A top 10 US bank manages CLO portfolios totaling billions in assets, each governed by contracts up to 500 pages.
global media company
Conversational, decision-grade
responses in 15 seconds
A global media intelligence firm analyzes hundreds of millions of sources daily – from public news, social, and broadcast to proprietary analyst-curated databases – to help large enterprise clients manage communications, reputation, and strategic decision-making. Their competitive advantage is the layer on top of publicly available data: in-house human editorial teams, proprietary scoring and analytics frameworks, and years of analyst judgment refined into decision-grade intelligence. When a crisis signal is building or a competitor’s narrative is gaining traction, speed and accuracy matter enormously. Historically, getting an answer meant waiting for a human analyst to manually aggregate across those sources: a process measured in hours, not seconds.
Image
Deploying production AI in <60 days to accelerate claims review 67%
A leading global firm transforming insurance subrogation operations with AI found that manual review processes capped their throughput to ~30% of available claims.
Image

For models that need to be right. Not just good enough.