[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"cheat-sheet---en":3,"domain-info---en":3,"topic-info----en":3,"lesson-aws-certified-cloud-practitioner-cloud-technology-and-services-ai-ml-and-analytics-analytics-services-en":4,"next-aws-certified-cloud-practitioner-cloud-technology-and-services-ai-ml-and-analytics-analytics-services-en":18,"prev-aws-certified-cloud-practitioner-cloud-technology-and-services-ai-ml-and-analytics-analytics-services-en":311},null,{"locked":5,"reason":6,"meta":7,"item":3},true,"paywall",{"title":8,"description":9,"isFree":10,"estimatedMinutes":11,"difficulty":12,"learningObjectives":13},"AWS Analytics Services","Learn the core AWS analytics services: Amazon Athena, Redshift, EMR, AWS Glue, Amazon Kinesis and Data Firehose, QuickSight, Lake Formation, OpenSearch Service, and how they fit into a data pipeline.",false,18,"beginner",[14,15,16,17],"Describe the stages of a typical AWS analytics pipeline: ingest, store, process, query, and visualize","Match the core analytics services to the job each one does","Compare Amazon Athena, Amazon Redshift, and Amazon EMR","Identify which services handle real-time streaming data",{"locked":10,"reason":3,"meta":19,"item":28},{"title":20,"description":21,"isFree":5,"estimatedMinutes":22,"difficulty":12,"learningObjectives":23},"Application Integration Services","Learn the AWS application integration services that connect decoupled components: Amazon SQS for message queues, Amazon SNS for pub/sub fan-out, Amazon EventBridge for event routing, and AWS Step Functions for workflow orchestration.",16,[24,25,26,27],"Explain why application integration services help you build decoupled, event-driven systems","Describe what Amazon SQS, Amazon SNS, Amazon EventBridge, and AWS Step Functions each do","Compare a message queue (SQS) with a pub/sub topic (SNS)","Match a described integration need to the right AWS service",{"id":29,"title":20,"body":30,"description":21,"difficulty":12,"estimatedMinutes":22,"extension":236,"infographics":237,"isFree":5,"learningObjectives":257,"meta":258,"navigation":5,"path":259,"quiz":260,"seo":308,"stem":309,"__hash__":310},"courses/courses/aws-certified-cloud-practitioner/en/domains/03-cloud-technology-and-services/08-other-aws-services/01-application-integration.md",{"type":31,"value":32,"toc":224},"minimark",[33,38,42,45,50,54,57,60,63,80,83,87,90,93,97,100,103,107,110,113,116,120,123,126,129,133,200,204],[34,35,37],"h2",{"id":36},"why-this-matters","Why this matters",[39,40,41],"p",{},"A modern application is rarely one program. It is many small parts that hand work to each other: a web layer takes an order, another component charges the card, a third updates inventory, and a fourth sends an email. If those parts call each other directly, one slow or failed component can freeze the whole system.",[39,43,44],{},"Application integration services solve this. They let the parts of an application talk to each other without being tightly connected, which is called decoupling. The components pass messages or events through a managed service instead of calling each other directly, so one part can fail, slow down, or scale up on its own without breaking the rest. The CLF-C02 exam tests 4 of these services at a recognition level: Amazon SQS, Amazon SNS, Amazon EventBridge, and AWS Step Functions. Your job is to match a described need to the right one.",[46,47],"infographic",{"alt":48,"slug":49},"A comparison of the four AWS application integration services: Amazon SQS as a message queue, Amazon SNS as a pub/sub topic, Amazon EventBridge as a rule-based event bus, and AWS Step Functions as a step-by-step workflow.","messaging-services-comparison",[34,51,53],{"id":52},"amazon-sqs-message-queues","Amazon SQS: message queues",[39,55,56],{},"Amazon Simple Queue Service (Amazon SQS) is a fully managed message queue. A producer puts messages into the queue, and a consumer pulls them out to process one at a time, at its own pace. The queue stores the messages in between, so the producer and consumer never have to be available at the same moment.",[39,58,59],{},"This is the classic way to decouple a fast front end from slower back-end work. Imagine a website that accepts photo uploads. Instead of making the user wait while each photo is resized, the site drops a message in an SQS queue and responds right away. A separate worker reads the queue and resizes the photos when it can. If the worker falls behind or restarts, the messages wait safely in the queue.",[39,61,62],{},"SQS offers 2 queue types you should recognize by name:",[64,65,66,74],"ul",{},[67,68,69,73],"li",{},[70,71,72],"strong",{},"Standard queues"," give maximum throughput and at-least-once delivery, with best-effort ordering.",[67,75,76,79],{},[70,77,78],{},"FIFO queues"," (first-in, first-out) guarantee that messages are processed exactly once, in the exact order they were sent.",[39,81,82],{},"Think of SQS as point-to-point: each message is meant for one consumer to handle.",[34,84,86],{"id":85},"amazon-sns-pubsub-fan-out","Amazon SNS: pub/sub fan-out",[39,88,89],{},"Amazon Simple Notification Service (Amazon SNS) is a managed publish/subscribe (pub/sub) messaging service. Publishers send messages to a topic, and the topic pushes a copy of each message to every subscriber. This is many-to-many, or fan-out: one message reaches many destinations at once.",[39,91,92],{},"Subscribers can be SQS queues, AWS Lambda functions, HTTP/S endpoints, and even end users through SMS, email, and mobile push. So SNS is the service to reach for when a single event needs to trigger several reactions in parallel, or when you need to send notifications to people.",[46,94],{"alt":95,"slug":96},"A fan-out diagram showing a publisher sending one message to an Amazon SNS topic, which delivers copies in parallel to two SQS queues and a Lambda function.","sns-sqs-fanout",[39,98,99],{},"A very common design is SNS plus SQS together. The publisher sends one message to an SNS topic, and the topic delivers it to several SQS queues. Each queue feeds a different consumer, so billing, shipping, and analytics can all react to the same order event without knowing about each other.",[39,101,102],{},"The fastest way to tell SNS and SQS apart: SQS is a queue that one consumer pulls from, while SNS pushes each message to many subscribers.",[34,104,106],{"id":105},"amazon-eventbridge-the-event-bus","Amazon EventBridge: the event bus",[39,108,109],{},"Amazon EventBridge is a serverless event bus. An event bus receives a stream of events and routes each one to the right place based on rules you define. A rule matches events by their content, then sends matching events to one or more targets, such as a Lambda function, an SQS queue, or Step Functions.",[39,111,112],{},"What sets EventBridge apart is where the events come from. It can receive events from your own applications, from many AWS services, and from third-party SaaS applications like Zendesk or Shopify. That makes it the natural choice for building event-driven systems that react to activity across tools you do not control.",[39,114,115],{},"A simple way to hold the distinction: SNS broadcasts a message to its subscribers, while EventBridge inspects each event and routes it by rules, including events from SaaS partners.",[34,117,119],{"id":118},"aws-step-functions-orchestrating-workflows","AWS Step Functions: orchestrating workflows",[39,121,122],{},"The first 3 services move individual messages or events. AWS Step Functions is different: it coordinates a whole sequence of steps as a single workflow.",[39,124,125],{},"You define the steps as a visual workflow (a state machine), and Step Functions runs them in order, passes data from one step to the next, retries steps that fail, and tracks the state of the entire process. This is orchestration. It fits any multi-step job where order and error handling matter, such as processing an order, running a data pipeline, or approving a request.",[39,127,128],{},"Picture an order workflow: validate the payment, then reserve inventory, then send a confirmation. If reserving inventory fails, Step Functions can retry it or branch to a different path, all without you writing the plumbing to track where the process is.",[34,130,132],{"id":131},"putting-them-side-by-side","Putting them side by side",[134,135,136,152],"table",{},[137,138,139],"thead",{},[140,141,142,146,149],"tr",{},[143,144,145],"th",{},"Service",[143,147,148],{},"What it is",[143,150,151],{},"Reach for it when",[153,154,155,167,178,189],"tbody",{},[140,156,157,161,164],{},[158,159,160],"td",{},"Amazon SQS",[158,162,163],{},"Managed message queue (pull-based)",[158,165,166],{},"You need to decouple components and let one consumer process messages at its own pace",[140,168,169,172,175],{},[158,170,171],{},"Amazon SNS",[158,173,174],{},"Pub/sub messaging (push-based)",[158,176,177],{},"One message must fan out to many subscribers, or you need to notify people by SMS, email, or push",[140,179,180,183,186],{},[158,181,182],{},"Amazon EventBridge",[158,184,185],{},"Serverless event bus",[158,187,188],{},"You need to route events by rules, especially from AWS services or SaaS apps",[140,190,191,194,197],{},[158,192,193],{},"AWS Step Functions",[158,195,196],{},"Workflow orchestration",[158,198,199],{},"You need to run a multi-step process in order, with retries and error handling",[34,201,203],{"id":202},"exam-tips","Exam tips",[64,205,206,209,212,215,218,221],{},[67,207,208],{},"Application integration services exist to decouple the parts of an application so they can fail and scale independently.",[67,210,211],{},"Amazon SQS is a message queue. One consumer pulls each message. Standard queues favor throughput, FIFO queues guarantee order and exactly-once processing.",[67,213,214],{},"Amazon SNS is pub/sub. It fans out one message to many subscribers (SQS queues, Lambda, HTTP, SMS, email, push). SNS plus SQS is the classic fan-out pattern.",[67,216,217],{},"Tell SQS and SNS apart: SQS is a queue one consumer reads, SNS pushes to many subscribers at once.",[67,219,220],{},"Amazon EventBridge is a serverless event bus that routes events by rules and can ingest events from SaaS applications.",[67,222,223],{},"AWS Step Functions orchestrates multi-step workflows with built-in ordering, retries, and error handling. Pick it when a scenario describes coordinating several steps.",{"title":225,"searchDepth":226,"depth":226,"links":227},"",3,[228,230,231,232,233,234,235],{"id":36,"depth":229,"text":37},2,{"id":52,"depth":229,"text":53},{"id":85,"depth":229,"text":86},{"id":105,"depth":229,"text":106},{"id":118,"depth":229,"text":119},{"id":131,"depth":229,"text":132},{"id":202,"depth":229,"text":203},"md",[238,247],{"slug":49,"concept":239,"style":240,"aspectRatio":241,"labels":242},"Four contrasting message topologies side by side, one per integration service. Amazon SQS shows a queue that a single consumer pulls from at its own pace; Amazon SNS shows one message pushed to many subscribers at once; Amazon EventBridge shows a bus whose rules route each event to the right target; AWS Step Functions shows an ordered chain of steps with retries built in. The orange accent marks the fan-out point of the SNS topic, the sharpest visual contrast with the one-consumer queue beside it. Takeaway: pick the service by how the message needs to move, not by the message itself.","comparison","16:9",[243,244,245,246],"SQS: queue, one consumer pulls","SNS: one message pushed to many","EventBridge: rules route each event","Step Functions: ordered steps with retries",{"slug":96,"concept":248,"style":249,"aspectRatio":241,"labels":250},"A one-to-many fan-out showing a publisher sending a single message to an Amazon SNS topic, which copies it in parallel to every subscriber: an SQS queue feeding a billing consumer, another SQS queue feeding a shipping consumer, and a Lambda function reacting to the same event. All branches leave the topic at the same moment to show parallel delivery, with no subscriber aware of the others. The orange accent sits on the SNS topic at the center of the fan, the point where one message becomes many. Takeaway: publish once, and every system that cares gets its own copy to process independently.","diagram",[251,252,253,254,255,256],"Publisher sends one message","SNS topic copies to every subscriber","SQS queue: billing consumer","SQS queue: shipping consumer","Lambda reacts to the same event","All subscribers process in parallel",[24,25,26,27],{},"/courses/aws-certified-cloud-practitioner/en/domains/03-cloud-technology-and-services/08-other-aws-services/01-application-integration",{"passingScore":261,"questions":262},70,[263,272,276,284,289,294,300],{"question":264,"type":265,"options":266,"correctAnswer":268,"explanation":271},"What problem do AWS application integration services like Amazon SQS and Amazon SNS solve?","single",[267,268,269,270],"They store large files cheaply for long-term archiving","They let the parts of an application communicate without being tightly connected, so one component can fail or scale without breaking the others","They encrypt data at rest inside a database","They provide virtual desktops to remote employees","Application integration services decouple components, so a slow or failed part does not bring down the rest of the system. Archiving is Amazon S3 Glacier, encryption at rest is handled by services like AWS KMS, and virtual desktops are Amazon WorkSpaces.",{"question":273,"type":265,"options":274,"correctAnswer":160,"explanation":275},"Which AWS service is a fully managed message queue used to decouple components, where a producer sends messages that one consumer pulls and processes?",[171,160,193,182],"Amazon SQS is a message queue: a producer puts messages in, and a consumer pulls them out to process at its own pace. SNS is pub/sub fan-out, Step Functions orchestrates workflows, and EventBridge routes events.",{"question":277,"type":265,"options":278,"correctAnswer":279,"explanation":283},"What is the key difference between Amazon SQS and Amazon SNS?",[279,280,281,282],"SQS is a queue where one consumer pulls each message, while SNS is pub/sub where one message is pushed to many subscribers at once","SQS is for email and SNS is for SMS only","SQS runs on-premises while SNS runs in the cloud","There is no difference; they are the same service","SQS is a pull-based queue for point-to-point work, where each message is processed by one consumer. SNS is push-based pub/sub, where a single message fans out to many subscribers in parallel.",{"question":285,"type":265,"options":286,"correctAnswer":193,"explanation":288},"A team needs to coordinate a multi-step order process: validate payment, then reserve inventory, then send a confirmation, with automatic retries if a step fails. Which service is built for this?",[160,171,193,287],"Amazon S3","AWS Step Functions coordinates a sequence of steps as a visual workflow and handles ordering, retries, and error handling for you. SQS and SNS move individual messages but do not orchestrate a multi-step process.",{"question":290,"type":265,"options":291,"correctAnswer":182,"explanation":293},"Which AWS service is a serverless event bus that uses rules to route events from your applications, AWS services, and SaaS apps to targets like AWS Lambda?",[182,160,193,292],"Amazon Connect","Amazon EventBridge is a serverless event bus that matches events against rules and routes them to targets, and it can receive events from SaaS applications. SQS is a queue, Step Functions is a workflow service, and Connect is a contact center.",{"question":295,"type":265,"options":296,"correctAnswer":297,"explanation":299},"Amazon SNS can fan out a single published message to multiple subscribers at the same time, such as several SQS queues and a Lambda function.",[297,298],"True","False","A common pattern is SNS fan-out: a publisher sends one message to an SNS topic, and the topic delivers a copy to every subscriber in parallel, including SQS queues, Lambda functions, and HTTP endpoints. This lets several systems react to the same event independently.",{"question":301,"type":302,"options":303,"correctAnswers":306,"explanation":307},"Which two AWS services are most often used together so that one event can be delivered to several queues for parallel processing? (Select all that apply.)","multiple",[171,160,304,305],"AWS X-Ray","Amazon WorkSpaces",[171,160],"In the fan-out pattern, an SNS topic delivers each message to multiple SQS queues so different consumers can process the same event in parallel. X-Ray is for debugging and WorkSpaces is a virtual desktop service.",{"title":20,"description":21},"courses/aws-certified-cloud-practitioner/en/domains/03-cloud-technology-and-services/08-other-aws-services/01-application-integration","j7DUaU5UZPkScr3rZEkqUB91-nFvh0EUr9c4toO9_AE",{"locked":10,"reason":3,"meta":312,"item":320},{"title":313,"description":314,"isFree":5,"estimatedMinutes":11,"difficulty":12,"learningObjectives":315},"AWS AI and Machine Learning Services","Learn the AWS AI and ML stack: pre-trained AI services like Rekognition and Comprehend, the Amazon SageMaker platform for building your own models, and generative AI with Amazon Bedrock and Amazon Q.",[316,317,318,319],"Describe the three layers of the AWS AI and ML stack","Match common pre-trained AI services to the problems they solve","Explain what Amazon SageMaker is and how it differs from the pre-trained AI services","Identify Amazon Bedrock and Amazon Q as the AWS generative AI services",{"id":321,"title":313,"body":322,"description":314,"difficulty":12,"estimatedMinutes":11,"extension":236,"infographics":589,"isFree":5,"learningObjectives":599,"meta":600,"navigation":5,"path":601,"quiz":602,"seo":645,"stem":646,"__hash__":647},"courses/courses/aws-certified-cloud-practitioner/en/domains/03-cloud-technology-and-services/07-ai-ml-and-analytics/01-ai-ml-services.md",{"type":31,"value":323,"toc":581},[324,326,329,332,336,339,343,349,355,361,364,367,370,507,510,530,534,537,540,543,547,550,556,562,564],[34,325,37],{"id":36},[39,327,328],{},"AWS gives you machine learning at three very different levels of effort. You can call a ready-made AI service and get a result in one API request, you can build and train your own model on the Amazon SageMaker platform, or you can tap into generative AI with foundation models. The CLF-C02 exam does not ask you to train a model or write code. It asks you to recognize the main services and match a described problem to the right one.",[39,330,331],{},"This lesson maps out the AWS AI and ML stack so the names stop blurring together. You will see how the layers differ, what each pre-trained service is for, where SageMaker fits, and which services cover generative AI.",[34,333,335],{"id":334},"the-three-layers-of-the-aws-ai-stack","The three layers of the AWS AI stack",[39,337,338],{},"Think of AWS machine learning as three stacked layers, from least effort to most control.",[46,340],{"alt":341,"slug":342},"A diagram of the three layers of the AWS AI and ML stack: pre-trained AI services at the top, the Amazon SageMaker platform in the middle, and generative AI with Amazon Bedrock and Amazon Q at the bottom.","ai-ml-stack-three-layers",[39,344,345,348],{},[70,346,347],{},"Pre-trained AI services"," sit at the top. AWS already trained these models, so you send data to an API and get an answer back: a label for an image, the sentiment of a sentence, an audio file from text. No ML knowledge is needed. This is where most Cloud Practitioner questions land.",[39,350,351,354],{},[70,352,353],{},"The ML platform",", Amazon SageMaker, sits in the middle. You reach for it when the pre-trained services do not fit and you need to build, train, and deploy your own model on your own data. It still removes a lot of heavy lifting, but you are doing real ML work here.",[39,356,357,360],{},[70,358,359],{},"Generative AI"," is the newest layer. Amazon Bedrock and Amazon Q let you use foundation models to generate text, answer questions, and build assistants, without training a model from scratch.",[39,362,363],{},"A quick rule of thumb: if AWS already solved the problem, use a pre-trained service; if you need a custom model, use SageMaker; if you want generative AI, use Bedrock or Q.",[34,365,347],{"id":366},"pre-trained-ai-services",[39,368,369],{},"These services deliver ready-made intelligence through an API. You do not train anything. The exam expects you to know what each one does and to pick the right one for a scenario.",[134,371,372,384],{},[137,373,374],{},[140,375,376,378,381],{},[143,377,145],{},[143,379,380],{},"What it does",[143,382,383],{},"Typical use",[153,385,386,397,408,419,430,441,452,463,474,485,496],{},[140,387,388,391,394],{},[158,389,390],{},"Amazon Rekognition",[158,392,393],{},"Image and video analysis",[158,395,396],{},"Detect objects, people, text, and scenes; facial analysis and comparison; content moderation",[140,398,399,402,405],{},[158,400,401],{},"Amazon Comprehend",[158,403,404],{},"Natural language processing",[158,406,407],{},"Find sentiment, key phrases, entities, and language in text",[140,409,410,413,416],{},[158,411,412],{},"Amazon Textract",[158,414,415],{},"Extract text and data from documents",[158,417,418],{},"Pull text, tables, and form fields from scanned PDFs and images",[140,420,421,424,427],{},[158,422,423],{},"Amazon Translate",[158,425,426],{},"Language translation",[158,428,429],{},"Translate text between languages for websites and apps",[140,431,432,435,438],{},[158,433,434],{},"Amazon Polly",[158,436,437],{},"Text to speech",[158,439,440],{},"Turn written text into lifelike spoken audio",[140,442,443,446,449],{},[158,444,445],{},"Amazon Transcribe",[158,447,448],{},"Speech to text",[158,450,451],{},"Convert spoken audio into written text, such as subtitles or call transcripts",[140,453,454,457,460],{},[158,455,456],{},"Amazon Lex",[158,458,459],{},"Conversational interfaces",[158,461,462],{},"Build text and voice chatbots and IVR systems",[140,464,465,468,471],{},[158,466,467],{},"Amazon Kendra",[158,469,470],{},"Intelligent search",[158,472,473],{},"Search across enterprise documents and get direct answers",[140,475,476,479,482],{},[158,477,478],{},"Amazon Personalize",[158,480,481],{},"Recommendations",[158,483,484],{},"Generate individualized product and content recommendations",[140,486,487,490,493],{},[158,488,489],{},"Amazon Forecast",[158,491,492],{},"Time-series forecasting",[158,494,495],{},"Predict future values like demand or inventory from historical data",[140,497,498,501,504],{},[158,499,500],{},"Amazon Fraud Detector",[158,502,503],{},"Fraud detection",[158,505,506],{},"Spot potentially fraudulent online activity",[39,508,509],{},"A few pairs trip people up, so anchor them now:",[64,511,512,518,524],{},[67,513,514,517],{},[70,515,516],{},"Polly versus Transcribe."," Polly is text to speech (text goes in, audio comes out). Transcribe is speech to text (audio goes in, text comes out). They are mirror images.",[67,519,520,523],{},[70,521,522],{},"Comprehend versus Translate."," Comprehend analyzes what text means (sentiment, entities, language). Translate converts text from one language to another.",[67,525,526,529],{},[70,527,528],{},"Rekognition versus Textract."," Rekognition analyzes images and video for objects, people, and scenes. Textract pulls structured text and data out of documents like forms and tables.",[34,531,533],{"id":532},"amazon-sagemaker","Amazon SageMaker",[39,535,536],{},"Amazon SageMaker is the platform for building, training, and deploying your own machine learning models. You use it when the pre-trained services do not cover your problem and you need a model trained on your specific data, such as predicting equipment failure from your own sensor readings.",[39,538,539],{},"SageMaker provides the tools for the whole ML workflow in one place: preparing data, picking an algorithm, training the model, tuning it, and deploying it to make predictions. It manages the underlying infrastructure so you focus on the model rather than the servers.",[39,541,542],{},"For the exam, hold one clear line: a pre-trained AI service is a finished product you call through an API, while SageMaker is the workshop where you build a model yourself. If a question describes a team building and training a custom model, the answer is SageMaker.",[34,544,546],{"id":545},"generative-ai-amazon-bedrock-and-amazon-q","Generative AI: Amazon Bedrock and Amazon Q",[39,548,549],{},"Generative AI uses large foundation models to produce new content, such as text, summaries, and answers. AWS offers two services you should recognize.",[39,551,552,555],{},[70,553,554],{},"Amazon Bedrock"," is a fully managed service that makes foundation models from Amazon and leading AI companies available through a single API. You can experiment with these models, customize them with your own data, and build generative AI applications without managing any infrastructure or training a model from scratch. Bedrock is the service for developers building generative AI features into their own apps.",[39,557,558,561],{},[70,559,560],{},"Amazon Q"," is a generative AI assistant. Amazon Q Business answers questions, summarizes information, and completes tasks using your company's internal data, which helps employees work faster. Amazon Q Developer helps with coding, testing, debugging, and working with AWS resources. Think of Q as a ready-to-use assistant, where Bedrock is the building block for your own generative AI apps.",[34,563,203],{"id":202},[64,565,566,569,572,575,578],{},[67,567,568],{},"The AWS AI stack has three layers: pre-trained AI services (call an API), Amazon SageMaker (build your own model), and generative AI (Amazon Bedrock and Amazon Q).",[67,570,571],{},"Pre-trained AI services need no ML expertise. Match the service to the task: Rekognition (images and video), Comprehend (text meaning), Textract (data from documents), Translate (languages), Polly (text to speech), Transcribe (speech to text), Lex (chatbots), Kendra (search), Personalize (recommendations), Forecast (time-series prediction), Fraud Detector (fraud).",[67,573,574],{},"Remember the mirror pairs: Polly is text to speech, Transcribe is speech to text.",[67,576,577],{},"Amazon SageMaker is the platform to build, train, and deploy custom models. Pick it when a scenario involves building a model on your own data.",[67,579,580],{},"Amazon Bedrock gives access to foundation models through one API for building generative AI apps. Amazon Q is a ready-to-use generative AI assistant.",{"title":225,"searchDepth":226,"depth":226,"links":582},[583,584,585,586,587,588],{"id":36,"depth":229,"text":37},{"id":334,"depth":229,"text":335},{"id":366,"depth":229,"text":347},{"id":532,"depth":229,"text":533},{"id":545,"depth":229,"text":546},{"id":202,"depth":229,"text":203},[590],{"slug":342,"concept":591,"style":249,"aspectRatio":241,"labels":592},"A vertical stack of the three AWS machine learning layers with an effort-versus-control axis running down its side. Pre-trained AI services sit at the top, called through an API with no ML work; Amazon SageMaker sits in the middle for building and training your own models on your own data; the generative AI layer sits at the base with Amazon Bedrock as the building block for your own apps and Amazon Q as the ready-to-use assistant, both using foundation models with no training from scratch. The orange accent highlights the top pre-trained layer, where most Cloud Practitioner questions land. Takeaway: less effort as you move up the stack, more control as you move down.",[593,594,595,596,597,598],"Pre-trained services: call an API, no ML","SageMaker: build and train your own model","Generative AI: foundation models, no training","Bedrock: building block for your own apps","Amazon Q: ready-to-use assistant","Less effort above, more control below",[316,317,318,319],{},"/courses/aws-certified-cloud-practitioner/en/domains/03-cloud-technology-and-services/07-ai-ml-and-analytics/01-ai-ml-services",{"passingScore":261,"questions":603},[604,612,616,621,625,629,637,641],{"question":605,"type":265,"options":606,"correctAnswer":607,"explanation":611},"What is the main difference between the AWS pre-trained AI services (like Amazon Rekognition) and Amazon SageMaker?",[607,608,609,610],"Pre-trained AI services work through an API with no model building, while SageMaker is a platform to build, train, and deploy your own models","Pre-trained AI services cost more because they include support, while SageMaker is always free","Pre-trained AI services run only on-premises, while SageMaker runs only in the cloud","There is no difference; they are different names for the same product","The pre-trained AI services give you ready-made intelligence through a simple API call, with no ML expertise required. Amazon SageMaker sits one layer down: it is the platform you use when you need to build, train, and deploy a custom model on your own data.",{"question":613,"type":265,"options":614,"correctAnswer":445,"explanation":615},"A media company wants to add subtitles to its videos by automatically converting the spoken audio into text. Which AWS service fits best?",[434,445,423,401],"Amazon Transcribe is the speech-to-text service, so it turns spoken audio into written text for subtitles. Polly does the reverse (text to speech), Translate converts between languages, and Comprehend analyzes the meaning of text.",{"question":617,"type":302,"options":618,"correctAnswers":619,"explanation":620},"Which of the following are pre-trained AI services that you can use through an API without any ML expertise? (Select all that apply.)",[390,401,456,533],[390,401,456],"Rekognition, Comprehend, and Lex are pre-trained AI services that work through an API with no model building required. SageMaker is the build-your-own-model platform, which is a different layer of the stack.",{"question":622,"type":265,"options":623,"correctAnswer":434,"explanation":624},"Which AWS service turns written text into lifelike speech?",[445,412,434,467],"Amazon Polly is the text-to-speech service that produces lifelike spoken audio from text. Transcribe goes the other way (speech to text), Textract extracts text from scanned documents, and Kendra is an intelligent search service.",{"question":626,"type":265,"options":627,"correctAnswer":456,"explanation":628},"A developer wants to build a text and voice chatbot to handle customer questions. Which service is purpose-built for this?",[456,390,489,423],"Amazon Lex builds conversational interfaces (chatbots) using the same speech recognition and natural language understanding that powers Alexa. Rekognition handles images and video, Forecast predicts time-series data, and Translate converts languages.",{"question":630,"type":265,"options":631,"correctAnswer":633,"explanation":636},"What does Amazon Bedrock provide?",[632,633,634,635],"A 1/18th scale race car for learning reinforcement learning","Access to foundation models from Amazon and other AI companies through a single API, for building generative AI applications","A service that extracts text from scanned PDFs and forms","A managed data warehouse for business intelligence","Amazon Bedrock is the managed generative AI service that makes foundation models available through one API, so you can build generative AI apps without managing the underlying infrastructure. The race car describes AWS DeepRacer, and the other options describe Textract and Amazon Redshift.",{"question":638,"type":265,"options":639,"correctAnswer":297,"explanation":640},"Amazon Rekognition is the right service to identify objects, people, and text in images and video.",[297,298],"Amazon Rekognition adds image and video analysis to your applications: it can identify objects, people, text, and scenes, and run facial analysis and comparison. It requires no ML expertise to use.",{"question":642,"type":265,"options":643,"correctAnswer":478,"explanation":644},"A retailer wants to show each shopper individualized product recommendations based on their browsing and purchase history. Which AWS service is built for this?",[467,401,478,434],"Amazon Personalize creates individualized recommendations using the same technology behind recommendations on Amazon.com. Kendra is enterprise search, Comprehend analyzes text, and Polly produces speech.",{"title":313,"description":314},"courses/aws-certified-cloud-practitioner/en/domains/03-cloud-technology-and-services/07-ai-ml-and-analytics/01-ai-ml-services","Cpn7E4eIOrI6HDOOm8qNpf4lz5lhk3N3J650vkLH3Lc"]