Impact
$43M
Annual ROI
95%
Accuracy (up from 54%)
90%
of complex cases resolved in <24 hrs
The challenge
The challenge
This Top 5 Global Telco aimed to evolve its internal billing co-pilot into a customer-facing chatbot capable of serving its global customer base. However, the project stalled at 54% accuracy due to data blind spots and reasoning errors that frustrated efforts to launch.
The solution
The solution
Snorkel used cutting-edge data development frameworks to embed the telco’s subject-matter expertise directly into the GenAI application. This included creating a rigorous evaluation workflow and data development acceleration techniques that scaled human-in-the-loop expertise, enabling the application to accurately resolve even the most complex edge case.
The outcome
The outcome
In just a few months, the team drove model accuracy from 54% to 95%, enabling a successful global rollout to 80,000 daily customers. This high-performance system now resolves 90% of the most problematic billing cases in under 24 hours, delivering $43 million in annual ROI.
More customer stories
View all stories
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. This bottleneck left significant revenue on the table and froze their ability to scale. The path to automation was further blocked by severe data imbalances where the critical signals for coverage appeared in only a small fraction of claims, making traditional AI models unreliable.
DIU enhances decision-making resilience with Snorkel AI
Strategic dominance in the Indo-Pacific relies on the ability to track and coordinate friendly forces — ”blue objects” — with absolute precision. To maintain operational awareness in dynamic and contested environments, the Department of War identified a requirement for adaptable, dual-use technologies that enhance logistics and decision-making resilience.
