This lab provides experience working with Amazon Quick to create spaces and custom chat agents.

In this lab, you use Amazon Quick to automate an HR employee onboarding workflow. You create Quick spaces populated with HR policy documents, conduct AI-guided research on remote work best practices using Amazon Quick Research, build automated flows from natural language conversations, integrate Quick with an external HR API using an OpenAPI action connector, and design a multi-step onboarding flow that creates employee records, sends welcome emails, and generates IT setup tickets.

This lab provides hands-on experience using both Amazon Q Developer and Amazon Kiro in a single IDE experience.

This lab provides practice improving the security posture of a DevOps deployment using the Kiro CLI.

This lab shows a typical journey faced by agent developers when moving from agent prototype, built using Strands SDK, to production agents using Amazon Bedrock AgentCore.

In this lab, you build AI agents that understand natural language, use custom tools, and coordinate with other agents to solve complex financial problems using Amazon Bedrock and Strands SDK. By the end, you will have deployed a production-ready multi-agent system using Amazon Bedrock AgentCore.

Learners will work to create an AWS management assistant with Strands Agents SDK. The core Bedrock model will enable general reasoning, while Strands tools will allow analyzing local files, running python scripts, searching the web, and taking actions on AWS. At the end all the agents they've created will be used as tools in a multi-agent architecture.

In this lab, you create an AWS DevOps Agent Space, start an investigation from an active CloudWatch alarm, and use DevOps Agent to identify the root cause of a DynamoDB throttling issue and apply a mitigation plan.

This lab focuses on implementing multi-agent collaboration for AnyCompany's customer service request system using Amazon Bedrock and AWS services.

This lab guides learners through designing and implementing autonomous agents using Amazon Bedrock. Learners will create agents capable of independent decision-making, task execution, and problem-solving while maintaining alignment with business objectives. The lab emphasizes autonomous behavior configuration and complex task handling. This lab will focus on building the components using Bedrock APIs through a Jupyter notebook.

This lab teaches learners how to implement security guardrails for agentic AI applications using AWS services. The lab focuses on practical implementation of security controls, monitoring, and governance for AI agents interacting with AWS services. Learners will configure guardrails to ensure secure, controlled, and auditable AI agent behaviors. This lab will focus on building the components using Amazon Bedrock APIs through an Amazon SageMaker Jupyter notebook.

In this lab, you use AWS DevOps Agent to investigate and resolve three application failures across serverless, compute, and database services. You fix an S3 bucket policy error, review EC2 scaling and RDS connection recommendations, and configure webhook automation so CloudWatch alarms automatically trigger DevOps Agent investigations.

In this lab series, you've gained hands-on experience working with AWS Agentic AI services. Next, take the feedback survey to let us know your understanding of the topics covered and your suggestions for this course.