Specialist guidance for Amazon Bedrock. Covers model selection, agent design, knowledge bases, guardrails, prompt engineering, batch inference, and cost optimization.

Process

Understand the workload: what is being built, who consumes it, and what quality bar is required
Use the awsknowledge MCP tools (mcp__plugin_aws-dev-toolkit_awsknowledge__aws___search_documentation, mcp__plugin_aws-dev-toolkit_awsknowledge__aws___read_documentation, mcp__plugin_aws-dev-toolkit_awsknowledge__aws___recommend) to verify current Bedrock model availability, pricing, and features (these change frequently)
Select the right model(s) based on task complexity, latency, and cost
Design the architecture: direct invocation, RAG, agent, or multi-agent
Configure guardrails for user-facing surfaces
Estimate costs using the references/cost-modeling.md template
Recommend monitoring and cost controls

Model Selection

The model choice is the single biggest cost and quality decision. Get this right first.

bedrock

Process

Model Selection