Amazon Bedrock Knowledge Bases (managed RAG)
Fastest path to grounded chat over enterprise documents. Bedrock owns embeddings, chunking defaults, and retrieval APIs so your team ships the product layer.
- Compare: Bedrock vs SageMaker
GenAI decision tree
Which AWS GenAI Approach Should I Use?
Pick Amazon Bedrock, SageMaker, Agents, or a RAG stack by data sensitivity, customization needs, and team capacity — in 4 questions, with the comparison guide that goes deeper.
Last updated: August 5, 2026Author: FactualMinds AWS ArchitectsReviewed by: AWS Solutions Architect — Professional certified
Step 1/Choose to begin
What are you trying to ship first?
Start from the product outcome. Model choice follows the workload shape.
Recommendation
How to use this tree
This tree mirrors how we scope GenAI engagements: start from the product outcome (RAG, agents, generation, training), then decide how much infrastructure you want to own. The goal is a defensible default in under a minute — not an exhaustive catalog of every Bedrock model ID.
If two leaves feel close, walk both and read the comparison guides. The most common healthy starting shape is Bedrock foundation models + Knowledge Bases for RAG, with Agents only when tool use is required.
All possible recommendations in this tree
Reference list of every endpoint in this decision tree — useful when you want to skim before answering questions, or when JavaScript is disabled.
Custom RAG (OpenSearch / Aurora pgvector / S3 Vectors) + Bedrock
You own the retrieval plane; Bedrock (or SageMaker endpoints) owns generation. Right when chunking, hybrid search, or eval harnesses need to be first-class.
- Compare: Bedrock vs SageMaker
Amazon Q Business (existing deployments) / Quick Suite path
Enterprise assistant path for knowledge work without building a custom agent runtime. Prefer for IT/knowledge-worker assistants; not for productized customer-facing agents.
Amazon Bedrock Agents
Managed agent runtime for tool use, knowledge bases, and multi-step reasoning without standing up your own orchestrator.
- Compare: Bedrock Agents vs Step Functions
Step Functions + Bedrock (deterministic agentic workflows)
When the workflow is the product — retries, human approval, audit trails — put Step Functions in charge and call Bedrock as a step.
- Compare: Bedrock Agents vs Step Functions
Amazon Bedrock foundation models (prompt-first)
Invoke Claude, Llama, Titan, and other FMs via Bedrock APIs. Start here for summarization, classification, and generation before you fine-tune.
- Compare: Bedrock vs SageMaker
Amazon Bedrock fine-tuning / continued pre-training
Customize a Bedrock-supported model on your labeled corpus without owning training clusters. Raise the eval bar before production.
- Compare: Bedrock vs SageMaker
Amazon SageMaker (training & custom serving)
Full ML platform control — training jobs, pipelines, endpoints, and experiment tracking. Choose when Bedrock abstractions are the bottleneck.
- Compare: Bedrock vs SageMaker
SageMaker + custom agent runtime
When agent behavior is tightly coupled to models you train and serve yourself. Higher ops cost; justified only with an ML platform team.
Frequently Asked Questions
Should every GenAI app start on Bedrock?
Most product teams should. Bedrock removes GPU capacity management and gives multi-model choice behind one API. Move to SageMaker when you hit hard limits on customization, training control, or existing MLOps investment — not because SageMaker sounds more “serious.”
When is RAG better than fine-tuning?
RAG wins when answers must cite changing enterprise documents. Fine-tuning wins when you need style, format, or domain language that prompting cannot stabilize. Many production systems use both: RAG for facts, light fine-tuning or strong system prompts for behavior.
Where do Bedrock Agents fit vs Step Functions?
Use Bedrock Agents when the model must choose tools dynamically in a conversation. Use Step Functions when the workflow graph is mostly known, long-running, and must be auditable. See the Bedrock Agents vs Step Functions comparison for the breakpoint.
Want a deeper review than the tree?
Send us your workload requirements and we'll write back with a one-page architecture recommendation — usually within two business days.