Après avoir suivi ces cours, je me sens confiant dans la création de visualisations et de tableaux de bord professionnels.
Shoebur RahmanSpécialiste des marchés publics, Giz Bangladesh
Description du cours
Learn to design, build, evaluate, and deploy AI agent systems using the open-source Strands Agents SDK. Starting from core concepts like the agent loop and tool integration through to multi-agent orchestration and cloud deployment with Amazon Bedrock AgentCore.
Prérequis
Ce cours ne requiert aucun prérequis.
Programme de formation
Plan du cours
1
Agent Fundamentals
Learn how AI agents work, how to configure different model providers, connect tools with MCP, and add callbacks and streaming to your agent harness.
- Agent Harnesses and The Agent Loop50 XP
- Understanding Agent Harnesses50 XP
- Model Providers50 XP
- Configuring Model Providers50 XP
- MCP & The Tools Ecosystem50 XP
- Callbacks and Streaming50 XP
- Tools and Callbacks50 XP
- An agent harness is best described as50 XP
- What happens after a tool finishes executing50 XP
- Why use a different model for evaluations50 XP
- What security risk with agent tools50 XP
- Why suppress the default output handler50 XP
2
Agent Control
Control your agent's behavior with hooks, extend it with plugins and skills, and improve reliability using Strands Steering.
3
Memory & Context
Master context engineering, conversation management, and persistent memory with session managers.
4
Multi-Agent Systems
Build sophisticated multi-agent systems using agents-as-tools, graph workflows, and agent swarms.
5
Production
Evaluate your agents thoroughly and deploy them to the cloud with Amazon Bedrock AgentCore.
R
Building AI Agent Harnesses with Strands Agents
Cours
terminé
