Amazon Bedrock Cheat Sheet

Updated 2026-03-17

Next Topic: Chain-of-Thought Reasoning Cheat Sheet

Amazon Bedrock is a fully managed service from AWS that provides API-based access to foundation models from leading AI companies including Anthropic, AI21 Labs, Cohere, Meta, Mistral AI, Stability AI, and Amazon's own models. Rather than managing infrastructure, model hosting, or model training from scratch, developers can access state-of-the-art foundation models through a single unified API, customize them with proprietary data through fine-tuning or RAG, and build generative AI applications at scale with enterprise-grade security and privacy controls. Bedrock abstracts away the complexity of provisioning compute, managing model lifecycles, and securing inference endpoints, enabling teams to focus on application logic and business value. A key mental model to keep in mind: Bedrock is a model marketplace + inference runtime + customization toolkit — it's not a single model but an orchestration layer that lets you compare, customize, and operationalize many models using consistent tooling, with built-in safeguards like Guardrails to enforce compliance and responsible AI policies across all your generative AI workloads.

What This Cheat Sheet Covers

This topic spans 19 focused tables and 156 indexed concepts. Below is a complete table-by-table outline of this topic, spanning foundational concepts through advanced details.

Table 1: Core Service ComponentsTable 2: Foundation Model ProvidersTable 3: Inference ModesTable 4: Model Customization TechniquesTable 5: Knowledge Bases and RAGTable 6: Agents and OrchestrationTable 7: Security and ComplianceTable 8: Pricing ComponentsTable 9: APIs and IntegrationTable 10: Inference Configuration ParametersTable 11: Guardrails ConfigurationTable 12: Monitoring and ObservabilityTable 13: Advanced CustomizationTable 14: Model Providers and SelectionTable 15: Regions and AvailabilityTable 16: Prompt Management and OptimizationTable 17: Best PracticesTable 18: Error Handling and TroubleshootingTable 19: Use Cases and Applications

Table 1: Core Service Components

Component	Example	Description
Foundation Models (FMs)	Claude 3.5, Llama 3, Titan, Nova	• Pre-trained large language models, image generators, and embedding models from multiple providers available via unified API • each model optimized for different tasks (reasoning, code, vision, etc.).
Model Invocation	`InvokeModel`, `InvokeModelWithResponseStream`	• Synchronous or streaming inference calls to foundation models • supports on-demand and provisioned throughput modes.
Converse API	`Converse`, `ConverseStream`	• Unified multi-turn conversation interface that works across all text models • provides consistent message format regardless of underlying model.
Knowledge Bases	S3 → embeddings → OpenSearch	• Managed RAG (Retrieval Augmented Generation) pipeline • automatically chunks, embeds, and indexes documents into vector stores for context-aware responses.
Agents	Agent with action groups + knowledge bases	Autonomous AI assistants that break down tasks, call APIs, query knowledge bases, and orchestrate multi-step workflows using foundation models.
Guardrails	Content filters, PII redaction, topic policies	• Configurable safety and compliance controls applied to both inputs and outputs • blocks harmful content, enforces responsible AI policies.

Table 1: Core Service Components

Component	Example	Description
Foundation Models (FMs)	Claude 3.5, Llama 3, Titan, Nova	• Pre-trained large language models, image generators, and embedding models from multiple providers available via unified API • each model optimized for different tasks (reasoning, code, vision, etc.).
Model Invocation	`InvokeModel`, `InvokeModelWithResponseStream`	• Synchronous or streaming inference calls to foundation models • supports on-demand and provisioned throughput modes.
Converse API	`Converse`, `ConverseStream`	• Unified multi-turn conversation interface that works across all text models • provides consistent message format regardless of underlying model.
Knowledge Bases	S3 → embeddings → OpenSearch	• Managed RAG (Retrieval Augmented Generation) pipeline • automatically chunks, embeds, and indexes documents into vector stores for context-aware responses.
Agents	Agent with action groups + knowledge bases	Autonomous AI assistants that break down tasks, call APIs, query knowledge bases, and orchestrate multi-step workflows using foundation models.
Guardrails	Content filters, PII redaction, topic policies	• Configurable safety and compliance controls applied to both inputs and outputs • blocks harmful content, enforces responsible AI policies.