IBS Software’s Cargo system processes thousands of bilingual cargo logistics email messages daily, extracting critical information such as air waybill (AWB) numbers, flight details, weights, and delivery instructions in both English and Japanese. Challenges included manual intervention that slowed operations and a trade-off between accuracy and cost. IBS Software needed an AI solution that could accurately identify 23 different entity types across two languages while remaining cost-effective at scale. Using managed distillation capabilities of Amazon Bedrock, IBS Software distilled knowledge from Amazon Nova Pro into the more efficient Amazon Nova Lite model, achieving 95.085 percent F1-Score accuracy while reducing operational costs by 14x. IBS’s team of nine researchers and engineers spent approximately 4 months developing and deploying this solution. The project timeline included Month 1: dataset preparation and annotation of 500 bilingual email messages; Month 2: challenges with open-source frameworks (PyTorch, TextBrewer); Month 3: successful distillation using Amazon Bedrock (Nova Pro → Nova Lite); Month 4: production deployment and optimization. Key tasks included annotating 500 cargo email messages (350 English, 150 Japanese) with 23 entity types, configuring Amazon Bedrock distillation with custom hyperparameters, and training the student model for 4 epochs.