Quibank app: now on the App Store — free, works offline. Get the app ↗

Chapters0/41 ▾
  1. 1.Cloud Concepts: Benefits & Economics0/4
    1. The six advantages of cloud computing
    2. Elasticity, scalability, agility, high availability and global reach
    3. Cloud economics: fixed versus variable cost and total cost of ownership
    4. Licensing, rightsizing and automation
  2. 2.Cloud Concepts: Well-Architected & Migration0/5
    1. The six pillars of the Well-Architected Framework
    2. Pillar trade-offs and the AWS Well-Architected Tool
    3. The AWS Cloud Adoption Framework: outcomes, perspectives and phases
    4. Migration strategies: the 7 Rs
    5. AWS migration services and tools
  3. 3.Security: Shared Responsibility & Compliance0/4
    1. Security of the cloud and security in the cloud
    2. How responsibility shifts with the service you choose
    3. Compliance reports, programs and where data lives
    4. Encryption, keys and audit records
  4. 4.Security: IAM & Access Management0/4
    1. The root user and sign-in credentials
    2. IAM users, user groups and roles
    3. Policies, deny rules and least privilege
    4. Federation, IAM Identity Center, Amazon Cognito and secrets
  5. 5.Security: Services & Resources0/4
    1. Blocking web attacks and DDoS: AWS WAF, AWS Shield and AWS Firewall Manager
    2. Detecting threats, flaws and sensitive data: GuardDuty, Inspector and Macie
    3. Collecting, investigating and advising: Security Hub, Detective and Trusted Advisor
    4. AWS Marketplace and where to find security help
  6. 6.Technology: Deployment & Global Infrastructure0/4
    1. Ways to access AWS: console, CLI, SDKs and APIs
    2. Deployment tools and cloud deployment models
    3. Regions, Availability Zones and high availability
    4. Multiple Regions, data residency and edge services
  7. 7.Technology: Compute & Networking0/4
    1. Amazon EC2 instance types, auto scaling and load balancers
    2. Containers, serverless compute, Lightsail and AWS Batch
    3. Inside a VPC: subnets, gateways, security groups and network ACLs
    4. Route 53 and connecting networks to AWS
  8. 8.Technology: Databases & Storage0/4
    1. Relational databases: Amazon RDS, Aurora and databases on EC2
    2. NoSQL, in-memory and graph databases, plus database migration
    3. Amazon S3 object storage, storage classes and lifecycle policies
    4. Block and file storage, Storage Gateway, AWS Backup and disaster recovery
  9. 9.Technology: AI, Analytics & Other Services0/4
    1. AI and machine learning services: pre-trained services and SageMaker AI
    2. Analytics services: Glue, Athena, Redshift, EMR, OpenSearch, Kinesis and Amazon Quick
    3. Messaging and workflows: SQS, SNS, EventBridge, Step Functions, Amazon Connect and SES
    4. Developer tools, cloud desktops, AWS Amplify and AWS IoT Core
  10. 10.Billing, Pricing & Support0/4
    1. EC2 purchasing options: On-Demand, Spot, Savings Plans, Reserved Instances and dedicated hardware
    2. Data transfer costs, consolidated billing and cost allocation tags
    3. Cost management tools: Pricing Calculator, Cost Explorer, Budgets, Cost and Usage Reports and Compute Optimizer
    4. AWS Support plans, Trusted Advisor, AWS Health and where to get help
Saved in this browser. Move it to another device →
← Technology: AI, Analytics & Other Services

Chapter 9 · Lesson 1 of 4

AI and machine learning services: pre-trained services and SageMaker AI

1 min read

AWS splits AI into two groups. Pre-trained services do one common task through an API, so a team with no machine learning staff can use them right away.

Amazon SageMaker AI is the fully managed service for teams that want to build, train and deploy their own models on their own data, such as a bank's credit-risk model. If the scenario says no ML expertise, pick a pre-trained service; if it says train our own model, pick SageMaker AI.

ServiceInput to output
Amazon TranscribeSpeech to text
Amazon PollyText to lifelike speech
Amazon TranslateText in one language to another language
Amazon ComprehendText to meaning, such as positive or negative sentiment
Amazon TextractScanned documents to text, forms and tables
Amazon RekognitionImages and video to labels, including unsafe content flags
Amazon LexConversations: chatbots and voice bots that understand intent

Example: a clinic wants recorded voicemails in Spanish summarized as English text with a mood score. That chain is Transcribe, then Translate, then Comprehend: speech to text, change the language, then measure sentiment.

Check yourself

1. A support center wants to turn recorded customer calls into text and then use that text to measure whether each customer's opinion was positive or negative. Which pair of services does each job, in order?

2. A photo-sharing community has no machine learning staff. It wants to automatically flag uploaded pictures that show violence or other unsafe content. Which service fits best?

Facts checked 2026-11-15 · Sources: AWS Certified Cloud Practitioner (CLF-C02) exam guide, Domain 3, Amazon SageMaker AI Developer Guide: What is Amazon SageMaker AI

AWS Cloud Practitioner cheat sheet: every key fact on one page →