AIP-C01 cheat sheet

Exam at a glance

Domain weightings

How much of the exam each domain covers. Spend your study time in proportion — the heavier the domain, the more questions you'll see.

Key terms

Amazon Bedrock

Amazon Bedrock is a fully managed service that provides access to foundation models from multiple providers through a single API. AIP-C01 centers on Bedrock for building generative AI applications on AWS.

Foundation model

A foundation model (FM) is a large model pre-trained on broad data that can be adapted to many tasks. AIP-C01 covers selecting, evaluating, and integrating foundation models into applications.

Retrieval Augmented Generation

Retrieval Augmented Generation (RAG) is a technique that grounds a model's responses in retrieved external data rather than relying only on its training. AIP-C01 covers RAG with vector stores and knowledge bases.

Vector store

A vector store is a database that indexes embeddings so semantically similar content can be retrieved by nearest-neighbor search. AIP-C01 covers vector stores as the retrieval layer for RAG solutions.

Embedding

An embedding is a numeric vector representation of text or other data that captures semantic meaning. AIP-C01 covers generating and using embeddings for retrieval and RAG.

Knowledge base

A knowledge base in Amazon Bedrock is a managed capability that ingests and indexes your data so foundation models can retrieve it for grounded responses. AIP-C01 covers building knowledge bases for RAG.

Bedrock Agents

Amazon Bedrock Agents are a capability that lets foundation models plan and carry out multi-step tasks by calling tools and APIs through action groups. AIP-C01 covers agentic AI solutions built with Bedrock Agents.

Prompt engineering

Prompt engineering is the practice of designing prompts — including instructions, examples, and templates — to steer a model's output. AIP-C01 covers prompt engineering and prompt management techniques.

Bedrock Guardrails

Amazon Bedrock Guardrails are a capability that filters harmful content and enforces denied topics and policies on model inputs and outputs. AIP-C01 covers guardrails as a core Responsible AI control.

Responsible AI

Responsible AI is the practice of building AI systems that are safe, fair, transparent, and privacy-preserving. AIP-C01 covers implementing Responsible AI with guardrails, content filtering, and governance.

Prompt injection

Prompt injection is an attack in which crafted input manipulates a model into ignoring its instructions or leaking data. AIP-C01 covers detecting and mitigating prompt injection and jailbreaks.

Provisioned throughput

Provisioned throughput in Amazon Bedrock reserves dedicated model capacity for predictable, high-volume inference at a fixed rate. AIP-C01 covers it as a cost and performance optimization option.

Model evaluation

Model evaluation is the process of measuring a foundation model's output quality using automatic metrics or human review. AIP-C01 covers Bedrock model evaluation jobs for testing and validation.