Amazon.com Catalog Team builds self-learning generative AI at scale with Amazon Bedrock
Amazon's catalog system processes millions of daily product submissions requiring structured attribute extraction and title generation, but the traditional approach of having applied scientists analyze failures, update prompts, and redeploy could not scale to the volume and variety. Large models delivered accuracy but could not scale cost-efficiently; smaller models struggled with complex ambiguous cases.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Product listing submission
When a seller lists a new product, the catalog system must extract structured attributes and generate content such as titles.
Tools used
Amazon BedrockAmazon Nova LiteAnthropic Claude SonnetAmazon EC2Bedrock AgentCoreAmazon DynamoDBAmazon SQSAmazon CloudWatchAmazon Bedrock Runtime
Outcome
The self-learning system continuously improved accuracy while reducing costs, with error rates falling continuously through accumulated learnings rather than retraining, and the system evolving from generic understanding to domain-specific expertise.
What failed first
The existing manual improvement loop—scientists analyzing failures, updating prompts, testing, and redeploying—was resource-intensive and could not keep pace with the volume and variety of real-world catalog submissions.