Advanced Generative AI Development on AWS
Please note that this is not a prep course for any AWS certification!
This document contains links mentioned in the “Advanced Generative AI Development on AWS” course, and additional material on the same topics.
Module 0: Course Introduction
Full name: Advanced Generative AI Development on AWS
Product code: 300-MLAIDP-11
These links are based on the course version 1.1.5.
Online and classroom course options: Advanced Generative AI Development on AWS
The official course material: eVantage Bookshelf (VitalSource)
Lab environment: AWS Builder Labs
Additional material on AWS Skill Builder related to this course. Digital courses are free with a Skill Builder account; labs, SimuLearn and Cloud Quest need a Skill Builder subscription; AWS Jams are classroom events.
Skill Builder: Digital courses (free)
- Amazon Bedrock Getting Started
- Building Generative AI Applications Using Amazon Bedrock
- Amazon Bedrock AgentCore Getting Started
- AgentCore Evaluation on Amazon Bedrock
- Getting Started with Amazon Bedrock Managed Knowledge Bases
- Evaluate and Enhance RAG Performance with Amazon Bedrock
- Building cost-effective RAG applications with Amazon Bedrock Knowledge Bases and Amazon S3 Vectors
- Building Safe and Responsible Generative AI Applications with Amazon Bedrock Guardrails
- Prompt Engineering Best Practices for Amazon Bedrock Models
- Advanced Prompt Caching and Response Optimization
- Exploring Amazon Nova models using Amazon Bedrock
- Monitoring and Troubleshooting Generative AI Applications on AWS
Skill Builder: Self-paced labs (subscription required)
- Lab - Develop Retrieval Augmented Generation (RAG) Applications with Amazon Bedrock Knowledge Bases
- Lab - Develop Conversation Pattern with Amazon Bedrock APIs
- Lab - Building Secure and Responsible Gen AI with GuardRails for Amazon Bedrock
- Lab - Build and Evaluate RAG Applications using Knowledge Bases for Amazon Bedrock
- Lab - Explore Amazon Bedrock Agents integrated with Knowledge Bases and Guardrails
- Lab - Deploying Intelligent Agents with Amazon Bedrock AgentCore Runtime
- Lab - Enhance and Scale Agents with Amazon Bedrock AgentCore
- Lab - Monitor Agent Performance and Telemetry using AgentCore Observability
Skill Builder: Learning plans and exam prep
- Generative AI Learning Plan for Developers (includes labs)
- AWS Generative AI Developer Advanced Learning Plan (includes Labs)
- Builder Labs: Agentic AI on AWS
- Exam Prep Plan: AWS Certified Generative AI Developer - Professional (AIP-C01 - English)
- Exam Prep Plan: AWS Certified AI Practitioner (AIF-C01 - English)
- Exam Prep Plan: AWS Certified Machine Learning Engineer - Associate (MLA-C02 - English)
Skill Builder: Jams and game-based learning
- AWS Jam - Building Agentic AI with Amazon Bedrock AgentCore
- AWS Jam - Developing Generative AI Applications on AWS
- AWS Cloud Quest: Generative AI Practitioner
- AWS SimuLearn: Generative AI Architect
Recommended prerequisite course: Developing Generative AI Applications on AWS
Module 1: Foundation Model Selection and Configuration
Websites
- AWS Well-Architected Machine Learning Lens
- AWS Well-Architected Generative AI Lens
- AWS Solutions Constructs walkthrough, part 1
- AWS Solutions Constructs walkthrough, part 2
- Evaluate the performance of Amazon Bedrock resources
- Evaluate model performance using another LLM as a judge
- Use metrics to understand model performance
- Understanding intelligent prompt routing in Amazon Bedrock
- Route model inference requests across AWS Regions with cross-Region inference
- Optimize model inference for latency
- Monitor bedrock-runtime inference using CloudWatch metrics
- Amazon Bedrock Pricing
- Increase model invocation capacity with Provisioned Throughput in Amazon Bedrock
- Process multiple prompts with batch inference
- Create an application inference profile
- Analyzing your costs and usage with AWS Cost Explorer
- Managing your costs with AWS Budgets
- Circuit breaker pattern - AWS Prescriptive Guidance
- Retry with backoff pattern - AWS Prescriptive Guidance
- What is AWS AppConfig?
- Implement Lambda canary deployments using a weighted alias
- What is Amazon Nova?
- Claude in Amazon Bedrock (Claude Developer Platform)
- FMBench - Foundation Model Benchmarking Tool (aws-samples, GitHub)
- Amazon Bedrock Model Multiplexer (aws-samples, GitHub)
Blog posts
- Using the circuit breaker pattern with AWS Step Functions and Amazon DynamoDB
- Beyond the basics: A comprehensive foundation model selection framework for generative AI
- LLM-as-a-judge on Amazon Bedrock Model Evaluation
- Announcing the AWS Well-Architected Generative AI Lens
- Multi-LLM routing strategies for generative AI applications on AWS
- Use Amazon Bedrock Intelligent Prompt Routing for cost and latency benefits
- Building self-recovering systems against technology and business risk with Amazon Bedrock production resilience
- Effective cost optimization strategies for Amazon Bedrock
- Track, allocate, and manage your generative AI cost and usage with Amazon Bedrock
- Timeouts, retries, and backoff with jitter (Amazon Builders’ Library)
Videos
- Model Evaluation in Amazon Bedrock to compare & choose the right FMs (Amazon Web Services, 2024)
- Amazon Bedrock: Fast-track gen AI from prototype to production (Amazon Web Services, 2025)
- AWS re:Invent 2024 - Keynote with Dr. Swami Sivasubramanian
- What is AWS AppConfig? (Amazon Web Services)
Module 2: Advanced Data Processing for Foundation Models
Websites
- AWS Glue Data Quality
- Data Quality Definition Language (DQDL) reference
- Detecting PII entities (Amazon Comprehend)
- What is Amazon Macie?
- Remove PII from conversations by using sensitive information filters
- HIPAA Compliance - AWS
- GDPR - AWS
- Data lineage in Amazon DataZone
- Transform unstructured data into meaningful insights using Amazon Bedrock Data Automation
- How Bedrock Data Automation works
- Guidance for Multimodal Data Processing Using Amazon Bedrock Data Automation
- What is Amazon Textract?
- What is Amazon Transcribe?
- Multimodal understanding - Amazon Nova 2
- Vision (Claude Developer Platform)
- Amazon S3 Event Notifications
- Using Lambda with Amazon SQS
- Using Map state in Distributed mode for large-scale parallel workloads in Step Functions
- Inference using the Converse API
- Prompt caching for faster model inference
- Monitor your token usage by counting tokens before running inference
- What is Amazon ElastiCache?
- Multimodal RAG sample with Bedrock Data Automation (aws-samples, GitHub)
Blog posts
- Optimizing cost and latency with Amazon Bedrock prompt caching for Anthropic models
- Effectively use prompt caching on Amazon Bedrock
- Simplify multimodal generative AI with Amazon Bedrock Data Automation
- Building a multimodal RAG based application using Amazon Bedrock Data Automation and Amazon Bedrock Knowledge Bases
- Protect sensitive data in RAG applications with Amazon Bedrock
- Improve speed and reduce cost for generative AI workloads with a persistent semantic cache in Amazon MemoryDB
- Effective context engineering for AI agents (Anthropic)
- Prompt caching with Claude
- Getting started with AWS Glue Data Quality from the AWS Glue Data Catalog
- Intelligent document processing with Amazon Textract, Amazon Bedrock, and LangChain
Videos
- Measure and Monitor Data Quality of your Datasets in AWS Glue Data Catalog (Amazon Web Services)
- Measure and Monitor Data Quality in your ETL Pipeline (Amazon Web Services)
- What is Amazon Transcribe? (Amazon Web Services)
- Quit Tokenmaxxing: 4 Context Engineering Techniques for AI Agents (AWS Developers, 2026)
- AWS re:Invent 2024 - Revolutionizing Audi’s tender process with generative AI (AIM120)
Module 3: Vector Databases and Retrieval Augmentation
Websites
- Retrieve data and generate AI responses with Amazon Bedrock Knowledge Bases
- How Amazon Bedrock knowledge bases work
- Build a managed knowledge base
- Connect a data source to your knowledge base
- Connect to Microsoft SharePoint for your knowledge base
- How content chunking works for knowledge bases
- Use a custom transformation Lambda function to define how your data is ingested
- Configure and customize queries and response generation
- Improve the relevance of query responses with a reranker model in Amazon Bedrock
- RetrieveAndGenerate - Amazon Bedrock API Reference
- Create a service role for Amazon Bedrock Knowledge Bases
- Prerequisites for using a vector store you created for a knowledge base
- Vector search - Amazon OpenSearch Service
- k-Nearest Neighbor (k-NN) search in Amazon OpenSearch Service
- Working with vector search collections - Amazon OpenSearch Serverless
- Auto-optimize - Amazon OpenSearch Service
- Vector search performance tuning - OpenSearch Documentation
- Working with S3 Vectors and vector buckets
- Using S3 Vectors with Amazon Bedrock Knowledge Bases
- Using Aurora PostgreSQL as a Knowledge Base for Amazon Bedrock
- Amazon Titan Text Embeddings models
- Cohere Embed and Cohere Embed v4 models
- Custom classification - Amazon Comprehend
- aws-samples/amazon-bedrock-samples (GitHub)
Blog posts
- Amazon OpenSearch Service’s vector database capabilities explained
- Choose the k-NN algorithm for your billion-scale use case with OpenSearch
- Amazon Bedrock Knowledge Bases now supports advanced parsing, chunking, and query reformulation
- Contextual retrieval in Anthropic using Amazon Bedrock Knowledge Bases
- Dynamic metadata filtering for Amazon Bedrock Knowledge Bases with LangChain
- New APIs in Amazon Bedrock to enhance RAG applications, now available
- Introducing Amazon S3 Vectors: First cloud storage with native vector support at scale
- Building cost-effective RAG applications with Amazon Bedrock Knowledge Bases and Amazon S3 Vectors
- Optimizing vector search using Amazon S3 Vectors and Amazon OpenSearch Service
- Auto-optimize your Amazon OpenSearch Service vector database
- Amazon OpenSearch Service vector database capabilities revisited
- Hybrid Search with Amazon OpenSearch Service
- Use LangChain with PySpark to process documents at massive scale with Amazon SageMaker Studio and Amazon EMR Serverless
- Powering Billion-Scale Vector Search with OpenSearch (Uber Engineering)
- Introducing Contextual Retrieval (Anthropic)
- Improving RAG Systems with Amazon Bedrock Knowledge Base: Practical Techniques from Real Implementation
Videos
- AWS re:Invent 2024 - Build scalable RAG applications using Amazon Bedrock Knowledge Bases (AIM305)
- AWS re:Invent 2025 - Advanced agentic RAG Systems: Deep dive with Amazon Bedrock (AIM425)
- AWS re:Invent 2025 - Transforming AI storage economics with Amazon S3 Vectors (STG318)
- AWS re:Invent 2025 - Build Advanced Search with Vector, Hybrid, and AI Techniques (ANT314)
- AWS re:Invent 2025 - Build gpu-boosted, auto-optimized, billion-scale VectorDBs in hours (ANT213)
- Amazon S3 Vectors - Store and query vectors at scale in S3 (Amazon Web Services, 2025)
- How to use Aurora as a Knowledge Base for Amazon Bedrock for RAG - The Data Dive on AWS OnAir (Amazon Web Services, 2024)
Labs
- Lab 1: Develop Retrieval Augmented Generation (RAG) Applications with Amazon Bedrock Knowledge Bases, see Amazon Bedrock Knowledge Bases documentation
Module 4: Prompt Engineering and Governance
Websites
- Prompt engineering concepts - Amazon Bedrock
- Prompt engineering overview (Claude Developer Platform)
- Prompting best practices (Claude Developer Platform)
- Anthropic’s Interactive Prompt Engineering Tutorial (GitHub)
- Prompting best practices for Amazon Nova understanding models
- General best practices - Amazon Nova 2 prompt engineering
- Use a tool to complete an Amazon Bedrock model response
- Get validated JSON results from models - Amazon Bedrock
- Construct and store reusable prompts with Prompt management in Amazon Bedrock
- Deploy a prompt to your application using versions in Prompt management
- Amazon Bedrock Prompt Management (product page)
- Build an end-to-end generative AI workflow with Amazon Bedrock Flows
- Node types for your flow - Amazon Bedrock Flows
- Create a flow with a condition node - Amazon Bedrock Flows
- Converse with an Amazon Bedrock flow (multi-turn conversation)
- Amazon Bedrock Flows (product page)
- Monitor Amazon Bedrock API calls using CloudTrail
- AWS Generative AI Best Practices Framework v2 - AWS Audit Manager
- Security Compliance Management - AWS Artifact
Blog posts
- Structured data response with Amazon Bedrock: Prompt engineering and tool use
- Structured outputs with Amazon Nova: A guide for builders
- Structured outputs on Amazon Bedrock: Schema-compliant AI responses
- Amazon Bedrock Prompt Management: generally available
- Amazon Bedrock Flows is now generally available with enhanced safety and traceability
- Evaluating prompts at scale with Prompt Management and Prompt Flows for Amazon Bedrock
- AWS Audit Manager launches AWS Best Practices Framework for Generative AI
- Prompt Lifecycle Management on AWS - Amazon Bedrock Prompt Management, Versioning, and Prompt-as-Code CI/CD
- Effective Prompt Management in Amazon Bedrock: Versioning, Optimization, and Best Practices
Videos
- Prompting 101 - Code w/ Claude (Anthropic, 2025)
- Learn Better Prompt Engineering in 7 Minutes (AWS Developers)
- Demo - Amazon Bedrock Prompt Management (Amazon Web Services, 2024)
- Amazon Bedrock Prompt Optimization Demo (Amazon Web Services)
- Amazon Bedrock Flows Demo (Amazon Web Services)
- AI Conversations Made Simple: Overview of Amazon Bedrock Converse API (AWS Developers, 2024)
- Create a Superpowered AI Chatbot: Integrating Tools with Amazon Bedrock Converse API (AWS Developers)
Labs
- Lab 2: Develop conversation pattern with Amazon Bedrock APIs, see Carry out a conversation with the Converse API operations
Module 5: Implementing Agentic AI Frameworks with Amazon Bedrock AgentCore
Websites
- What is Amazon Bedrock AgentCore?
- Host agent or tools with Amazon Bedrock AgentCore Runtime
- Amazon Bedrock AgentCore Gateway: A secure AI gateway for agents, tools, and models
- Search for tools in your AgentCore gateway with a natural language query
- Add memory to your Amazon Bedrock AgentCore agent
- Interact with web applications using Amazon Bedrock AgentCore Browser
- Execute code and analyze data using Amazon Bedrock AgentCore Code Interpreter
- Provide identity and credential management for agent applications with Amazon Bedrock AgentCore Identity
- Policy in Amazon Bedrock AgentCore: Control Agent Interactions
- Observe your agent applications on Amazon Bedrock AgentCore Observability
- Evaluate agent performance with Amazon Bedrock AgentCore Evaluations
- Use interface VPC endpoints (AWS PrivateLink) for Amazon Bedrock AgentCore
- Amazon Bedrock Agents Classic maintenance mode
- Strands Agents - The open source toolkit for production AI agents
- Amazon Bedrock AgentCore Samples (awslabs GitHub)
- Model Context Protocol
- Claude Agent SDK overview
- LangGraph overview
- CrewAI Documentation
Blog posts
- Introducing Amazon Bedrock AgentCore: Securely deploy and operate AI agents at any scale
- Introducing Amazon Bedrock AgentCore Gateway: Transforming enterprise AI agent tool development
- Introducing Amazon Bedrock AgentCore Identity: Securing agentic AI at scale
- Amazon Bedrock AgentCore Memory: Building context-aware agents
- Secure ingress connectivity to Amazon Bedrock AgentCore Gateway using interface VPC endpoints
- Introducing Strands Agents, an Open Source AI Agents SDK
- Strands Agents SDK: A technical deep dive into agent architectures and observability
- Building agents with the Claude Agent SDK
- Building effective agents (Anthropic)
Videos
- AWS re:Invent 2025 - Bridging from POC to production: An intro to Amazon Bedrock AgentCore (AIM2204)
- AWS re:Invent 2025 - Scale agent tools with Amazon Bedrock AgentCore Gateway (AIM3313)
- AWS re:Invent 2025 - Securing agent access with Amazon Bedrock AgentCore Identity (SEC313)
- AWS re:Invent 2025 - Agents in the enterprise: Best practices with Amazon Bedrock AgentCore (AIM3310)
- AWS re:Invent 2025 - Improve agent quality in production with Bedrock AgentCore Evaluations (AIM3348)
- AWS re:Invent 2025 - Build agentic workflows on AWS with third-party agents and tools (AIM3311)
Module 6: AI Safety and Security
Websites
- Detect and filter harmful content by using Amazon Bedrock Guardrails
- Create your guardrail (Amazon Bedrock Guardrails components)
- What are Automated Reasoning checks in Amazon Bedrock Guardrails?
- Use the ApplyGuardrail API in your application
- Identity and access management for Amazon Bedrock
- Data encryption (Amazon Bedrock)
- GuardDuty AI Protection
- OWASP Top 10 for LLM Applications
- Responsible AI - Building AI Responsibly - AWS
- ISO 42001 Artificial Intelligence Management System - AWS
- Amazon SageMaker Model Cards
- Bias Detection and Model Explainability - Amazon SageMaker Clarify
- Using Amazon Augmented AI for Human Review
- What is Nitro Enclaves?
- AI Risk Management Framework (NIST)
Blog posts
- Safeguard your generative AI workloads from prompt injections
- Designing for the inevitable: System prompt leakage and mitigations in generative AI applications
- Amazon Bedrock Guardrails enhances generative AI application safety with new capabilities
- Tailor responsible AI with new safeguard tiers in Amazon Bedrock Guardrails
- Build reliable AI systems with Automated Reasoning on Amazon Bedrock - Part 1
- Implement model-independent safety measures with Amazon Bedrock Guardrails
- Elevate your AI security: Must-see re:Inforce 2025 sessions
- Methodology for incident response on generative AI workloads
Videos
- Automated Reasoning checks in Amazon Bedrock Guardrails (Amazon Web Services)
- AWS re:Invent 2025 - Enterprise AI Without the Chaos: A New Path to Secure, Compliant Applications
- AWS re:Invent 2025 - Can Your AI Show Its Work? Healthcare’s Critical Imperative for Explainable AI
- Automated Reasoning to Prevent LLM Hallucination with Byron Cook (The TWIML AI Podcast, 2024)
Labs
- Lab 3: Building Secure and Responsible Gen AI with Guardrails for Amazon Bedrock, see Amazon Bedrock Guardrails documentation
Module 7: Performance Optimization and Cost Management
Websites
- Application inference profiles
- Per-request metadata tagging
- How tokens are counted in Amazon Bedrock
- Using Amazon ElastiCache for Valkey for semantic caching
- Vector search - Amazon MemoryDB
- Context windows (Claude Developer Platform)
- Choosing the right model (Claude Developer Platform)
- Optimizing for cost and intelligence (Claude Developer Platform)
- Customize at the edge with Lambda@Edge
- Cost optimization - Generative AI Lens
Blog posts
- Lower cost and latency for AI using Amazon ElastiCache as a semantic cache with Amazon Bedrock
- Optimizing AI responsiveness: A practical guide to Amazon Bedrock latency-optimized inference
- Build a proactive AI cost management system for Amazon Bedrock - Part 1
- Build a proactive AI cost management system for Amazon Bedrock - Part 2
- Track generative AI costs with Amazon Bedrock inference profiles
- Optimize LLM Costs on Amazon Bedrock: From Billing Attribution to Operational Telemetry
- Enhance call center efficiency using batch inference for transcript summarization with Amazon Bedrock
Videos
- AWS re:Invent 2025 - Balance cost, performance & reliability for AI at enterprise scale (AIM3304)
- AWS re:Invent 2025 - Mastering model choice: The 3-step Amazon Bedrock advantage (AIM391)
- AWS re:Invent 2025 - Delighting Slack users safely and quickly with Amazon Nova and Bedrock (AIM384)
- AWS re:Invent 2025 - Build serverless chatbots using Amazon ElastiCache & Aurora PostgreSQL (DAT314)
Module 8: Monitoring and Observability for Generative AI
Websites
- Monitor model invocation using CloudWatch Logs and Amazon S3
- Diagnose InvocationLatency increases using output tokens per second (OTPS)
- Generative AI observability - Amazon CloudWatch
- Model Invocations - Amazon CloudWatch
- Add observability to your Amazon Bedrock AgentCore resources
- Use contextual grounding check to filter hallucinations in responses
- Monitor Amazon Bedrock Guardrails using CloudWatch metrics
- Using CloudWatch anomaly detection
- Detecting unusual spend with AWS Cost Anomaly Detection
- Configure model invocation logging in Amazon Bedrock by using AWS CloudFormation
- OpenTelemetry GenAI Semantic Conventions (GitHub)
- Observe - Advanced AgentCore observability concepts (awslabs samples)
- Operational excellence - Generative AI Lens
- Reduce hallucinations (Claude Developer Platform)
Blog posts
- Introducing Amazon CloudWatch Omni: Observability for the AI Era
- Use Guardrails to prevent hallucinations in generative AI applications
- Detect hallucinations for RAG-based systems
- Reducing hallucinations in large language models with custom intervention using Amazon Bedrock Agents
- Minimize AI hallucinations and deliver up to 99% verification accuracy with Automated Reasoning checks
- Observing and evaluating AI agentic workflows with Strands Agents SDK and Arize AX
- Monitor agents built on Amazon Bedrock with Datadog LLM Observability
- Calculating the Return on Investment (ROI) of AI
- Getting started with Tokenomics on AWS
Videos
- AWS re:Invent 2025 - Monitor the quality and accuracy of your generative AI workloads (COP418)
- AWS re:Invent 2025 - Tracing the Untraceable: Full-Stack Observability for LLMs and Agents (AIM212)
- AWS re:Invent 2025 - Elevate application and generative AI observability (COP326)
- AWS re:Invent 2025 - Observability for AI Agents and Traditional Workloads (COP335)
Module 9: Testing, Validation, and Continuous Improvement
Websites
- GSM8K: Grade School Math benchmark dataset (OpenAI, GitHub)
- HumanEval: evaluating large language models trained on code (OpenAI, GitHub)
- Evaluate the performance of RAG sources using Amazon Bedrock evaluations
- Creating a model evaluation job that uses human workers in Amazon Bedrock
- Amazon Bedrock Evaluations (product page)
- Foundation Model Evaluations Library (aws/fmeval, GitHub)
- Guidance for Evaluating Generative AI Applications using OSS on AWS
- What is Amazon Nova Act?
- Nova Act SDK (aws/nova-act, GitHub)
- Define success criteria and build evaluations (Claude Developer Platform)
- Ragas documentation
- DeepEval quickstart
- AWS Bedrock provider - Promptfoo
Blog posts
- New RAG evaluation and LLM-as-a-judge capabilities in Amazon Bedrock
- Evaluating RAG applications with Amazon Bedrock knowledge base evaluation
- Evaluate and improve performance of Amazon Bedrock Knowledge Bases
- Use custom metrics to evaluate your generative AI application with Amazon Bedrock
- Going beyond vibes: Evaluating your Amazon Bedrock workloads for production
- Build an automated generative AI solution evaluation pipeline with Amazon Nova
- Evaluate RAG responses with Amazon Bedrock, LlamaIndex and RAGAS
- Build reliable AI agents for UI workflow automation with Amazon Nova Act, now generally available
- Accelerating software delivery with agentic QA automation using Amazon Nova Act
Videos
- AWS re:Invent 2025 - Using Amazon Nova Act to simplify login workflows (AIM271)
- AWS re:Invent 2025 - Beyond web browsers: HITL and tool integration for Nova Act (AIM3334)
Module 10: Enterprise Integration Patterns
Websites
- Use interface VPC endpoints (AWS PrivateLink) to create a private connection between your VPC and Amazon Bedrock
- Identity-based policy examples for Amazon Bedrock
- Throttle requests to your REST APIs for better throughput in API Gateway
- Usage plans and API keys for REST APIs in API Gateway
- Use AWS WAF to protect your REST APIs in API Gateway
- What is IAM Identity Center?
- Define permissions based on attributes with ABAC authorization
- SAML 2.0 federation
- OIDC federation
- What Is Amazon EventBridge?
- Invoke and customize Amazon Bedrock models with Step Functions
- What Is AWS Cloud Map?
- What is AWS Outposts?
- What is AWS Direct Connect?
- What is AWS Lake Formation?
- DynamoDB global tables - multi-active, multi-Region replication
- Creating Amazon Route 53 health checks and configuring DNS failover
- Reliability - Generative AI Lens
- Guidance for Multi-Provider Generative AI Gateway on AWS
Blog posts
- Implementing least privilege access for Amazon Bedrock
- Build a dynamic, role-based AI agent using Amazon Bedrock inline agents
- Build a multi-tenant generative AI environment for your enterprise on AWS
- Build an internal SaaS service with cost and usage tracking for foundation models on Amazon Bedrock
- Getting started with cross-region inference in Amazon Bedrock
- Use AWS PrivateLink to set up private access to Amazon Bedrock
- Build generative AI apps using AWS Step Functions and Amazon Bedrock
Videos
- AWS re:Invent 2025 - Building Intelligent Workflows with Event Driven AI (MAM327)
- AWS re:Invent 2025 - Adding agentic AI to legacy apps with Amazon Bedrock AgentCore (MAM345)
- AWS re:Invent 2025 - Digital sovereignty and data residency with AWS Hybrid and Edge services (HMC310)
- AWS re:Invent 2025 - Multi-Region disaster recovery & resilience testing, feat. Fidelity (COP358)
Module 11: Course Wrap-up
Websites
- AWS Skill Builder
- AWS Classroom training
- AWS Certification
- AWS Certification exam preparation
- AWS Certification exams
- AWS Recertification
- Schedule an Exam
- AWS Ramp-Up Guides
- AWS Workshops
- AWS Training and Certification contact form
Courses
- Developing Generative AI Applications on AWS
- Spec-Driven Development with Kiro
- AWS Skill Builder courses
- AWS Builder Labs