Practice Exams:

Amazon

Amazon AWS AIP-C01: CI/CD for GenAI on AWS

Home/Amazon aip c01 ci cd for genai on awsCI/CD for generative AI on AWS has to version more than application code. Production behavior can change through prompts, foundation-model identifiers, inference profiles, Guardrails, Knowledge Bases, agent instructions, action groups, embedding models, retrieval settings, evaluation datasets, Lambda tools, and infrastructure. A release process that tracks only the web application can leave the most important AI behavior unreviewed.On this pageVersion prompts as production configurationVersion model and routing decisionsUse infrastructure as codeSeparate dev, test, and production dataRun model and RAG evaluation in the pipelineRun…

Read More

Amazon AWS AIP-C01: Bedrock Model Evaluation

Home/Amazon aip c01 bedrock model evaluationAmazon Bedrock evaluations provide several ways to compare model and RAG behavior with repeatable evidence. Current Bedrock supports programmatic model evaluations, human-based evaluation jobs, model evaluation with an LLM as judge, and LLM-based evaluation of knowledge bases or external RAG sources. The platform can score built-in or custom metrics and store evaluation datasets and results in Amazon S3.On this pageBuild a representative datasetUse programmatic evaluation for repeatabilityUse LLM-as-a-judge for qualitative metricsUse human evaluation where judgment mattersEvaluate RAG retrieval and generationCompare cost and latency alongside qualityUse…

Read More

Amazon AWS AIP-C01: Bedrock Knowledge Bases in Practice

Home/Amazon aip c01 bedrock knowledge bases in practiceAmazon Bedrock Knowledge Bases provides a managed retrieval layer for RAG applications. It can ingest supported data sources, create or use embeddings, store and retrieve chunks through supported vector stores, apply metadata filtering and reranking, and combine retrieval with generation through Bedrock runtime APIs. Newer capabilities also include structured data stores that translate natural-language questions into SQL and agentic retrieval that can decompose complex questions into subqueries.On this pageStart with authoritative sourcesChoose parsing and chunking deliberatelyUse metadata for business filtersUse reranking when first-stage…

Read More

Amazon AWS AIP-C01: Bedrock Agents and Tool Use

Home/Amazon aip c01 bedrock agents and tool useAmazon Bedrock Agents Classic can turn a foundation model into an orchestrator that can interpret a user request, decide which action or knowledge source is relevant, gather missing information, call tools, and return a final response. The architecture is powerful because the agent can bridge natural language and business APIs. The risk is that model reasoning now influences real systems, which makes tool design, identity, validation, user confirmation, and observability first-class engineering concerns.On this pageDesign action groups around business capabilitiesUse Lambda for controlled…

Read More

Amazon AWS AIP-C01: Amazon Bedrock Model Selection

Home/Amazon aip c01 amazon bedrock model selectionAmazon Bedrock model selection is no longer a simple choice between a few text models. The Bedrock catalog includes foundation models from multiple providers, model families with different modalities and context windows, multiple API compatibility options, in-Region and cross-Region inference, inference profiles, on-demand and provisioned capacity patterns, and model lifecycle differences.On this pageStart with the taskCheck API compatibilityCheck Regional availabilityUse inference profiles intentionallyEvaluate quality with real promptsMeasure latency and throughputInclude cost in the evaluationUse Guardrails separately from model choicePlan for model lifecycle AWS’s current…

Read More

Amazon AWS AIP-C01: API Gateway for GenAI Applications

Home/Amazon aip c01 api gateway for genai applicationsAmazon API Gateway can act as the governed front door for a generative AI application built on Amazon Bedrock. Instead of allowing each client to invoke foundation models directly, an API layer can enforce authentication, tenant isolation, quotas, throttling, request validation, Web Application Firewall controls, lifecycle versioning, and observability before the request reaches the Bedrock runtime.On this pagePut governance in front of model invocationChoose JWT or IAM authorization deliberatelyThrottle before the Bedrock quotaUse WAF for internet-facing APIsStream model responses where the UX needs…

Read More

Production ML on AWS

Production machine learning on AWS is the engineering of a model lifecycle that can be repeated, measured, governed, and operated. A notebook can prove that a model concept works, but a production service must also control data and feature versions, training cost, pipeline execution, artifact approval, deployment, monitoring, security, and recovery. The model is only one component of the system. Home/Amazon/Production ML on AWSAmazonPublished October 7, 2026On this pageMake reproducibility the entry requirementTreat features as production contractsOrchestrate the lifecycle instead of scripting itControl cost across training and servingDeploy the model…

Read More

Generative AI on AWS

Generative AI on AWS is an application-engineering discipline built around Amazon Bedrock, AWS identity and network controls, retrieval systems, agent tools, API boundaries, evaluations, deployment automation, and cost-aware runtime design. The durable architecture is not “call a foundation model.” It is a complete product path from authenticated user request through model or agent reasoning to grounded evidence, controlled actions, telemetry, and release lifecycle. Home/Amazon/Generative AI on AWSAmazonPublished October 7, 2026On this pagePut a governed API boundary in front of inferenceSelect models with production evidenceUse agents where model-driven orchestration adds valueBuild…

Read More

AWS Security Engineering

AWS Security Engineering is the discipline of turning cloud-security principles into controls that work consistently across accounts, identities, networks, data, workloads, and incident operations. The platform is highly composable: Organizations, IAM Identity Center, IAM, KMS, CloudTrail, Config, Security Hub, GuardDuty, Inspector, Macie, Security Lake, Control Tower, VPC controls, backup, and automation can all contribute. The engineering challenge is deciding where each control belongs, who owns it, and how it scales without making every workload dependent on a central security team for routine changes. Home/Amazon/AWS Security EngineeringAmazonPublished October 7, 2026On this…

Read More

AWS Cloud Operations

AWS Cloud Operations is the discipline of running cloud services after architecture diagrams and initial deployment are no longer enough. The operating model has to answer how fleets are managed, how deployments are released, how telemetry is organized, how incidents are triaged, how container capacity is supplied, and how network behavior is understood when the application crosses managed services and Kubernetes. The goal is not to know every console page. It is to make change, failure, and recovery predictable across AWS accounts and Regions. Home/Amazon/AWS Cloud OperationsAmazonPublished October 7, 2026On…

Read More

AWS Architecture in Practice

AWS Architecture in Practice is about turning AWS services into systems whose account boundaries, failure modes, data flows, messaging, recovery, cost, and operations can be explained and tested. The service catalog is large, but durable architecture relies on a smaller set of recurring decisions: isolate workloads into accounts, keep organization guardrails separate from workload permissions, decouple components that should fail independently, choose data and compute services according to access patterns, and design recovery from explicit RTO and RPO targets. Home/Amazon/AWS Architecture in PracticeAmazonPublished October 7, 2026On this pageStart with the…

Read More

Amazon AWS SAP-C02: Transit Gateway and Direct Connect

Enterprise connectivity becomes difficult long before an organization runs out of ways to connect one VPC to another. The real challenge is controlling route scale, segmentation, hybrid connectivity, failure behavior, and ownership as the number of VPCs, accounts, Regions, and data centers grows. Point-to-point designs can work at small scale, but they create a mesh of relationships that becomes increasingly hard to reason about. Home/Amazon/Amazon AWS SAP-C02: Transit Gateway and Direct ConnectAmazonPublished October 3, 2026On this pageTransit Gateway replaces connection sprawl with a hub-and-spoke modelTransit Gateway route tables are the…

Read More

Amazon AWS SAP-C02: Multi-Region AWS Design Starts With Business Continuity

Multi-Region architecture is often presented as the ultimate form of cloud resilience. In reality, it is one of several recovery strategies, and it carries significant cost and operational complexity. The first question should not be “How do we run in two AWS Regions?” It should be “What business interruption are we trying to survive, and how quickly must service and data recover?” Home/Amazon/Amazon AWS SAP-C02: Multi-Region AWS Design Starts With Business ContinuityAmazonPublished October 3, 2026On this pageHigh availability inside one Region is not the same as Regional disaster recoveryRTO and…

Read More

Amazon AWS SAP-C02: Organizations and SCPs: Guardrails at Scale

Identity policies answer what a principal is allowed to do. In a large AWS organization, architects also need a way to define what member accounts are never allowed to grant, even when local administrators have broad IAM authority. Service control policies, or SCPs, provide that organization-level permission boundary. They are powerful because they operate above individual account policy design, and dangerous when architects misunderstand what they do. Home/Amazon/Amazon AWS SAP-C02: Organizations and SCPs: Guardrails at ScaleAmazonPublished October 3, 2026On this pageSCPs are permission guardrails, not reusable IAM policiesOU design determines…

Read More

Amazon AWS SAP-C02: Modernization Patterns for Large AWS Migrations

Large cloud migrations fail when every application is treated as the same kind of move. A portfolio may contain simple virtual machines, commercial software, databases near end of support, tightly coupled legacy applications, systems that should be retired, and products that deserve a full redesign. Trying to force all of them through one migration pattern produces either unnecessary engineering or a large collection of cloud-hosted legacy problems. Home/Amazon/Amazon AWS SAP-C02: Modernization Patterns for Large AWS MigrationsAmazonPublished October 3, 2026On this pagePortfolio discovery comes before migration-wave planningRehost and relocate are useful…

Read More