Building Agentic AI: Amazon Nova Act and Strands Agents in Practice

Source: Dev.to

Introduction

Session introduction on the emergence of Agentic AI as a pivotal topic in the current AI landscape. Aimed at forward‑thinking developers looking beyond basic understanding to real‑world applications and innovations.

Future Trends of Agentic AI

• Overview of the evolution of generative AI, highlighting a progression from low agency (rule‑based, high human oversight) to high agency (independent operation, strategic decision‑making).
• Acknowledgment of the current stage of Agentic AI development, emphasizing the need for advanced technologies, governance, trust, and organizational readiness for higher agency.

Prediction by Sequoia Capital

Sequoia Capital’s keynote address on AI in 2025 envisions a future where AI systems evolve beyond tool‑like attributes to become autonomously operating intelligent agents. These agents will possess capabilities for reasoning, planning, collaboration, and high autonomous operation.

Vision for the 2030s Economy

Sequoia Capital predicts that the economy in the 2030s, particularly in Asia, will function like a global neural network composed of numerous AI agent operations forming an interconnected network.

Potential Personal Success

Designing an AI agent that gains widespread adoption, especially globally, could lead to significant personal financial success, potentially allowing one to become extremely wealthy.

Importance of the Prediction

This forecast is crucial for guiding developers and understanding what needs to be achieved in the future of AI development.

Emergence of One‑Person Unicorns

Sequoia Capital predicts the rise of “one‑person unicorns,” companies created and operated by a single individual with a valuation of $1 billion USD. This trend will shift labor structures and give rise to new organizational models where a single person can run an entire startup.

Need for a Stochastic Mindset

The world of AI agents requires developers to adopt a new way of thinking, moving away from traditional expectations of accuracy toward a more stochastic mindset. This involves adjusting how developers connect with and utilize large language models and AI technologies.

Preparation for the New Era of Agentic AI

Success in the era of Agentic AI requires not only technical preparation but also mental and organizational adjustments. Developers must be ready for changes in organizational structures and mental frameworks to thrive in this new era.

Foundational Infrastructure for Agentic AI in 2025

Communication protocols like MCP and A2A are being developed to enable interoperability among AI agents and their tools. AWS is actively participating in the standards committees for MCP and A2A, contributing decades of experience in distributed systems to enhance these future protocols.

AWS Agentic AI Portfolio

The portfolio is organized into three layers:

1. Infrastructure
2. AI and agent developer software
3. Application layers

The focus is on AI and agent development software and services, including SDKs for agents such as Amazon Nova Act and Strands Agents.

Practical Agentic AI Application: Local Weather Information

Local Weather Information Agent

• Built with Amazon Bedrock powered by Emerald and equipped with the Hong Kong Observatory website URL.
• Users can interact using natural language (English, Spanish, or Chinese) to inquire about the current weather in Hong Kong.
• The agent autonomously locates the information on the specified website and saves a screenshot for verification, demonstrating capability comparable to a human web‑scraping engineer.

Impact on Web Scraping Engineers

The era of Agentic AI has arrived, potentially impacting traditional web‑scraping roles. Developers may need to prepare for this transition using AWS services like Nova Act.

Implementation Details of the AI Agent

• Nova Act forecast functions guide the agent on which web pages to capture and what actions to perform.
• Natural language is used to assign tasks such as reading and extracting the 9‑day weather forecast from the Hong Kong Observatory website.

Ambitions of Developers

Many developers aim to build their own Agentic AI applications from scratch and maintain complete source‑code control. Open‑source Strands agents can help achieve this goal, allowing developers to control every line of code.

Challenges in Building Custom Agents

Developers need connectors that enable agents to interact with diverse enterprise systems.

Components Required for Customized AI Agent Systems

• Tools & MCP (Message Control Protocol): Enable agents to execute workflows (e.g., booking hotels, updating information, triggering processes).
• Memory:
  • Short‑term memory maintains context within a session.
  • Long‑term memory allows agents to learn and improve over time.
• Brain (Large Language Models): LLMs can be extended using techniques like ReACT (Reasoning, Acting, and Communicating Together), reflection, and Chain of Thought to plan, reflect, and reason step‑by‑step.
• Persona: Defines the agent’s identity and behavior (e.g., HR agent vs. DevOps agent).
• Observability & Guardrails: Provide safety, debuggability, and alignment with goals.

Challenges in Building Functional AI Agents

Building a truly functional AI agent requires substantial effort; up to 80‑90 % of the work may be unrelated to unique business logic and processes.

AWS Solution: Strands Agents

Strands Agents is an AWS‑contributed open‑source SDK that enables developers to build AI agents with minimal code. It simplifies development by leveraging state‑of‑the‑art LLMs for planning and Chain of Thought reasoning.

Demo: Creating Mathematical Animations with Strands Agents

Core Implementation Code (Python)

# imports
from strands import Agent
from strands.mcp import MCPClient

# establish MCP connection to Manim server
client = MCPClient(host="localhost", port=12345)
tools = client.get_tools()  # retrieve available tools from the server

# initialize the agent with the retrieved tools
agent = Agent(tools=tools)

# natural language prompt for a cubic function animation
prompt = "Create a 9‑second animation of the cubic function y = x**3 from x = -3 to x = 3."

# process the request
result = agent.run(prompt)

print(result)  # output includes video file path or status message

Workflow Overview

1. Left terminal: Runs the MCP (Message Control Protocol) server, connecting to the Manim MCP server via STDIO transport.
2. Right terminal: Runs the MCP client program, launching the video‑generation chat interface.

Users input natural‑language commands (e.g., “draw a cubic function from -3 to 3 in 9 seconds”). The agent processes the request, adapts if issues arise, and produces the animation.

Benefits of Multi‑Agent Collaboration

• Specialization: Agents focused on specific domains increase precision and provide more accurate answers.
• Combination: Integrating specialized agents yields richer, more comprehensive solutions.