Synthetic data generation pipeline leveraging Amazon Bedrock LLM to create realistic test datasets from schema metadata and feed templates. Streamlit Web UI connects to a Python Backend Service that orchestrates Amazon Bedrock for intelligent data synthesis, pulling context from a Knowledge Base of SAM documentation and feed structures. The Synthetic Data Generator consumes schema metadata and static feed file templates to produce structured test data output. This architecture enables rapid, compliant test data creation without exposing production data, reducing time-to-test for data-intensive applications. Fork and customize this diagram on Diagrams.so to adapt the pipeline for your domain-specific schemas and LLM prompts.