Agent Plugins & Skills

Chapter 6 of the Building AI Agent Harnesses with Strands Agents course. Individual tools solve individual problems. But some capabilities require multiple tools working together with specific hooks and prompt instructions to function correctly. That's what a plugin is: a packaged bundle of tools + hooks + system prompt additions that you attach to an agent as a unit.

Think of it this way: a "memory" capability isn't just a save_memory tool. It's the tool, plus a hook that loads relevant memories at the start of each turn, plus prompt instructions telling the agent when and how to save things. Shipping those separately means every developer re-invents the wiring. A plugin ships them together.

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 production operations (guardrails, observability, evaluation, cloud deployment).

Reading: https://go.aws/4f9ugnJ
Github Repo: https://go.aws/4vqRLim
Strands Agents SDK: https://go.aws/3TtHynG

Follow AWS Developers!
🆇 X: https://go.aws/4pgXN3F
💼 LinkedIn: https://go.aws/4vqRM5U

#AWS #AgentHarness #StrandsAgents

Видео Agent Plugins & Skills канала AWS Developers