Enrich messages in-flight with AI classification and entity extraction using Amazon EventBridge Pipes and Amazon Bedrock
Messages arrive in an Amazon SQS queue and are read by Amazon EventBridge Pipes.
The Pipe invokes an AWS Lambda enrichment function that calls Amazon Bedrock (Claude Sonnet 4.6) to classify sentiment, extract entities, and summarize the message.
The Pipe delivers the enriched output to its target, Amazon CloudWatch Logs. In parallel, the enrichment function persists each enriched record to Amazon DynamoDB for querying and downstream analytics.
< Back to all patterns
Clone repo
git clone https://github.com/aws-samples/serverless-patterns/cd serverless-patterns/eventbridge-pipes-bedrock-enrichment-cdkDeploy
<code>cd eventbridge-pipes-bedrock-enrichment-cdk/cdk</code><code>npm install</code><code>npx cdk deploy</code>Testing
Send a message to the Amazon SQS source queue.
Wait a few seconds for the Pipe to process.
Tail the Amazon CloudWatch Logs target log group (/pipes/bedrock-enriched-output) to see the enriched output delivered by the Pipe.
Query the Amazon DynamoDB table to see the persisted enriched record with sentiment, entities, and summary.
Cleanup
npx cdk destroyCreated by:
