AWS Certified Generative AI Developer – ProfessionalStudy guide

Learn to design GenAI solutions and select/configure the right foundation model (FM). Cover model evaluation in Amazon Bedrock, resilience via Cross-Region Inference, provisioned throughput, fine-tuning/LoRA, and the Well-Architected Framework (Generative AI Lens).

Learn pipelines that ensure quality of data fed to FMs: AWS Glue Data Quality, SageMaker Data Wrangler/Processing, multimodal processing (Transcribe, Textract), input formatting for the Bedrock API, and entity extraction with Comprehend.

Learn vector database design for FM augmentation: Amazon Bedrock Knowledge Bases, OpenSearch Service (vector search/Neural plugin), Aurora pgvector, DynamoDB, metadata frameworks, and freshness via incremental updates.

Learn mechanisms that improve RAG retrieval quality: chunking strategies, Titan embeddings, hybrid search, Bedrock reranker, query expansion/decomposition/transformation, and access via function calling/MCP.

Learn prompt strategies that control FM behavior and the governance around them: Bedrock Prompt Management (templates/versions/variant comparison), Bedrock Guardrails, chain-of-thought, Bedrock Prompt Flows, and auditing via CloudTrail/CloudWatch Logs.

Learn to implement agents that reason and use tools autonomously: multi-agent with Strands Agents/Agent Squad, tool integration via MCP (Model Context Protocol), Bedrock AgentCore, ReAct/stopping conditions with Step Functions, and MCP servers on Lambda/ECS.

Learn FM deployment matched to app needs: on-demand invocation with Lambda, Bedrock provisioned throughput, SageMaker endpoints, containers (GPU/memory/token throughput), and model cascading.

Learn to embed FM capabilities into existing enterprise environments: event-driven (EventBridge), GenAI gateway, identity federation/RBAC/least privilege, Outposts/Wavelength, and CI/CD with CodePipeline/CodeBuild.

Learn to integrate FM APIs robustly: sync/async (SQS), Bedrock streaming (WebSocket/SSE), exponential backoff/rate limiting/fallback, observability with X-Ray, and model routing.

Learn integrations and dev tools that accelerate GenAI apps: UI with Amplify, OpenAPI, no-code with Bedrock Prompt Flows, Bedrock Data Automation, Amazon Q Developer, and troubleshooting with CloudWatch Logs Insights/X-Ray.

Learn defense-in-depth against harmful inputs/outputs: input/output filtering with Bedrock Guardrails, toxicity/moderation, hallucination reduction (Knowledge Base grounding, JSON Schema), and prompt injection/jailbreak detection.

Learn data protection for FM deployments: isolation/access with VPC endpoints/IAM/Lake Formation, PII detection with Comprehend/Macie, data masking/anonymization, and retention with S3 Lifecycle.

Learn governance for compliance and traceability: SageMaker model cards, data lineage/catalog with Glue, CloudTrail auditing, and continuous monitoring (misuse, drift, policy violations, bias drift).

Learn to implement transparency, fairness, and accountability: reasoning display and source attribution, Bedrock agent tracing, fairness evaluation (CloudWatch metrics, A/B testing, LLM-as-a-judge), and stating limitations via model cards.

Learn strategies to reduce FM cost: token efficiency (context optimization, compression, pruning), model tiering, prompt caching/semantic caching, batch inference, and provisioned throughput optimization.

Learn to improve GenAI app responsiveness: latency-optimized models, parallel requests, streaming, tuning temperature/top-k/top-p, retrieval optimization, and Auto Scaling.

Learn observability for FM apps: token usage/hallucination rate/response quality in CloudWatch, Bedrock Model Invocation Logs, anomaly detection, tool-calling observability, and hallucination detection with golden datasets.

Learn to systematically evaluate FM output quality: Bedrock Model Evaluations, RAG evaluation, LLM-as-a-Judge, Bedrock Agent evaluations, A/B and canary testing, relevance/factual/consistency/fluency metrics, and regression testing.

Learn to isolate GenAI-specific issues: context window overflow, FM API integration problems, prompt issues, retrieval issues (embedding quality/drift), and prompt maintenance with schema validation, CloudWatch Logs/X-Ray.