AWS Step Functions provides managed orchestration for sequential service tasks and supports task-level `Retry` and `Catch` error handling. A state machine can invoke the three Amazon Bedrock agents in order and then invoke the rewards-calculation Lambda function. Configuring retry and catch branches for each task enables targeted recovery or fallback behavior when an individual agent or function fails, without maintaining custom Lambda orchestration and error-handling code. **Learn more:** [Handling errors in Step Functions workflows](https://docs.aws.amazon.com/step-functions/latest/dg/concepts-error-handling.html) · [Orchestrating Lambda functions with Step Functions](https://docs.aws.amazon.com/lambda/latest/dg/with-step-functions.html)
FREE QUESTION PREVIEWAWS Certified Generative AI Developer - Professional AIP-C01
AWS Certified Generative AI Developer - Professional AIP-C01
practice questions
Explore 12 free questions with the suggested answers and available explanations. No purchase is needed for this preview.
ADefine an Amazon API Gateway REST API behind each agent. Create a second Lambda function to orchestrate the calls to the agents and the rewards Lambda function. Configure the second Lambda function with a retry/fallback mechanism.
BCreate an AWS Step Functions state machine with four tasks that run the agents and the rewards Lambda function. Set up retry and catch branches for each of the task steps.
CConfigure each agent with a separate retry/fallback mechanism. Create a second Lambda function to orchestrate the calls to the agents and the rewards Lambda function. Define an Amazon API Gateway REST API behind the second Lambda function.
DCreate a second Lambda function to orchestrate the calls to the agents and the rewards Lambda function. Create an AWS Step Functions state machine with one task that runs the second Lambda function. Set up retry and catch branches for the task step.
Answer explanation