Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Building AI Agent Harnesses with Strands Agents

Amazon Web Services via Coursera

Go to class Write review

Details

Go to class

Provider

Coursera
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Effort

5 weeks, 1 hour a week
Sessions

Self-Paced
Level

Beginner
Subtitles

English

Found in

Overview

Google, IBM & Meta Certificates – 40% Off

One plan covers every Professional Certificate on Coursera.

Unlock All Certificates

This course teaches developers how to build AI agents and agent harnesses using the open-source Strands Agents SDK. The course starts by teaching what the difference between an agent and agent harness is, and progresses from fundamental concepts (the agent loop, model providers, tools) through intermediate patterns (hooks, plugins, steering, conversation management) to advanced multi-agent orchestration (agents-as-tools, graph workflows, agent swarms) and finally agent operations (observability, evaluation, cloud deployment). Each video introduces a core SDK primitive with working code examples, building toward a complete mental model of how all primitives compose together into a custom agent harness. By the end of the course, learners will be able to design, build, evaluate, and deploy agent systems using any model provider.

Syllabus

Agent Foundations

This module introduces the core concepts behind AI agents and agent harnesses. Learners explore how the agent loop enables reasoning, tool use, and response generation, while gaining hands-on experience configuring model providers and connecting external tools through MCP. By the end of the module, learners will understand the foundational building blocks that power agentic applications.

Customizing Agent Behavior

This module focuses on customizing and extending agent behavior. Learners discover how callbacks, streaming, hooks, plugins, skills, and steering mechanisms can be combined to create more interactive, controllable, and adaptable agent experiences. The module emphasizes how these primitives fit together within an agent harness to influence execution and outcomes.

Context Engineering, State, and Memory Management

This module examines what context engineering is and how agents maintain context across interactions. Learners explore conversation history management, state persistence, context window considerations, and session management patterns. These concepts provide the foundation for building agents that can support longer-running interactions and multi-user environments.

Multi-Agent Orchestration

This module introduces patterns for coordinating multiple agents to solve complex tasks. Learners build agent systems using delegation, graph-based workflows, and swarm architectures. The module demonstrates how individual agents can be combined into larger systems that distribute work, share context, and collaborate to achieve goals.

Production Agent Systems

This module focuses on preparing agent systems for production use. Learners explore evaluation methodologies, deployment architectures, scalability considerations, and operational best practices. By the end of the module, learners will understand how to measure agent performance and deploy reliable agent applications in cloud environments.