Chapter 2 of 5 · AWS AIF-C01
Fundamentals of GenAI
Core concepts, the model lifecycle, use cases, limits, model choice and AWS services for GenAI.
- 7topics
- 28 minfast track
- 1diagrams and exhibits
- 24%of the exam
Topics in this chapter
Take them in order, or jump to the one you need.
- 1Generative AI Core ConceptsLearn the core GenAI terms for AIF-C01: foundation models, LLMs, transformers, tokens, context windows, embeddings, diffusion…4 min
- 2Foundation Model LifecycleFollow the lifecycle of a foundation model from picking a model through pre training, adapting, evaluating, deploying and…4 min
- 3GenAI Use CasesIdentify common business use cases for generative AI such as summarisation, assistants, search and code generation, and match…4 min
- 4GenAI Capabilities and LimitationsWeigh the advantages of generative AI such as adaptability and speed against limits like hallucinations, inaccuracy, bias and…4 min
- 5Model Choice and Business MetricsChoose a GenAI model by performance, cost, speed and compliance needs, and measure business value with conversion, efficiency and…4 min
- 6AWS Services for GenAIKnow the AWS services for building GenAI apps: Amazon Bedrock, SageMaker JumpStart, PartyRock, the Amazon Q family and the Titan…Diagram4 min
- 7AWS GenAI Advantages and CostsUnderstand why building GenAI on AWS helps with speed, security and compliance, and weigh costs such as token pricing and…4 min
About this chapter
What this chapter covers
This chapter introduces generative AI (GenAI), the kind of AI that creates new text, images, audio and code. It explains the vocabulary, what GenAI is good and bad at, and which AWS services you use to build with it.
It follows the second domain of the AIF-C01 outline, which has three topics.
The first covers basic GenAI concepts and use cases. The second covers capabilities and limitations for business problems. The third covers AWS infrastructure and technologies for building GenAI applications.
How the topics fit together
The pages move from what GenAI is, to whether it suits a problem, to how you build it on AWS.
- Concepts and lifecycle define foundation models and the stages of building with them.
- Use cases show the tasks where GenAI adds value.
- Capabilities and limits teach you to balance benefits against risks such as hallucination.
- Model choice and metrics show how to pick a model and prove business value.
- AWS services and costs map each need to a service and explain the cost trade offs.
Most questions here are about matching a need to the right AWS service, or naming the right risk. Learn the one line purpose of each service.
How to use these pages
Each topic page has the same shape, so you can skim for what you need.
- What it is: the idea in plain words.
- How it works: the mechanism, with diagrams and tables.
- What to remember for the exam: the facts to memorise.
- Common mistakes: the classic traps.
- Check yourself: three questions to test your understanding.
Try the free playgrounds if you have an AWS account, since seeing a prompt and a response makes the terms easier to remember.
Ready for more practice?
The full AWS AIF-C01 question bank has 849 questions, with timed practice exams and an explanation for every answer.
This study guide is independent and is not affiliated with, endorsed by, or sponsored by AWS. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.