AI Agent Development on AWS

Build, deploy, and operate AI agents using Strands SDK, MCP, and Amazon Bedrock AgentCore.

Architecture Stack

Your Application CLI / API / Chat Strands SDK Agent logic + tools MCP Tool integration AgentCore Runtime + Ops USER-FACING FRAMEWORK PROTOCOL PLATFORM Runtime | Memory | Gateway Identity | Observability

Strands Agents SDK

Open-source Python/TypeScript SDK for building AI agents. Model-driven approach: the LLM decides what to do, not fixed code logic.

Single Agent

One agent with focused role, clear tools, straightforward prompts. Start here.

Agents-as-Tools

Wrap agents as callable tools. Parent agent invokes specialized child agents.

Swarms & Graphs

Parallel execution (swarms) or DAG-based workflows (graphs) for complex tasks.

Agent Handoffs

A2A protocol for seamless delegation between agents with context transfer.

Strands SDK docs →

Model Context Protocol (MCP)

An open standard for AI systems to communicate with tools, data sources, and services. Build tools once, integrate anywhere.

Tools

Callable actions with JSON schemas

Resources

Read-only persistent data

Prompts

Reusable instruction templates

Sample MCP server →

Amazon Bedrock AgentCore

Fully managed platform for deploying and operating AI agents at enterprise scale. Framework-agnostic, model-agnostic.

Runtime

Serverless execution

Memory

Session state

Gateway

Tool mediation

Identity

Access control

Observability

OpenTelemetry

AgentCore docs →

Get Started

The sample app includes a complete, working agent you can run in under 5 minutes.

# 1. Start the task API
cd sample-app && npm install && npm run dev

# 2. Install agent dependencies
cd agent && pip install -e ".[dev]"

# 3. Run the demo (no AWS needed)
python scripts/run-demo.py --mock

# 4. Or run interactively
python scripts/run-agent.py --mock
Agent code → Workshop Module 06 →