Which foundation models are supported?

The skill supports all models available via Amazon Bedrock, including Anthropic Claude 3.5 Sonnet, Haiku, Opus, and Amazon Titan.

What is the Amazon Bedrock Agents skill?

It is a specialized Claude Code capability that helps developers build, manage, and deploy autonomous agents using the Amazon Bedrock service for model orchestration.

How do action groups work within this skill?

Action groups allow your agents to perform tasks by invoking AWS Lambda functions or interacting with REST APIs defined by OpenAPI schemas.

Does it handle session management?

Yes, it manages session IDs and memory persistence, allowing your agents to maintain conversation context across multiple user interactions.

Can I use this skill to implement RAG?

Yes, this skill includes built-in support for connecting Bedrock Knowledge Bases to your agents, enabling Retrieval-Augmented Generation from your enterprise data.

Amazon Bedrock Agents

Name: Amazon Bedrock Agents
Author: adaptationio

byadaptationio

Data Science & ML

Builds and manages autonomous AI agents on Amazon Bedrock using foundation models, action groups, and knowledge bases.

About

This skill empowers developers to architect, deploy, and manage production-ready AI agents within the Amazon Bedrock ecosystem. It provides comprehensive patterns for orchestrating foundation models like Claude 3.5, integrating custom logic through Lambda action groups, and implementing sophisticated RAG patterns via Bedrock Knowledge Bases. By automating the configuration of agent aliases, session persistence, and runtime invocations, it streamlines the development of complex, multi-step workflows and conversational interfaces directly within the AWS cloud environment.

Key Features

Seamless integration of Lambda and OpenAPI action groups
Automated agent creation and foundation model orchestration
0 GitHub stars
Advanced session management and conversation context persistence
Deployment control via versioned aliases and environment routing
Configuration of Knowledge Bases for Retrieval-Augmented Generation (RAG)

Use Cases

Building enterprise-grade customer support agents with RAG capabilities
Orchestrating multi-step internal workflows involving AWS services
Developing autonomous tools that interact with private APIs and databases

About

Key Features

Seamless integration of Lambda and OpenAPI action groups
Automated agent creation and foundation model orchestration
0 GitHub stars
Advanced session management and conversation context persistence
Deployment control via versioned aliases and environment routing
Configuration of Knowledge Bases for Retrieval-Augmented Generation (RAG)

Use Cases

Building enterprise-grade customer support agents with RAG capabilities
Orchestrating multi-step internal workflows involving AWS services
Developing autonomous tools that interact with private APIs and databases