Switching Model Providers

Chapter 2 of the Building AI Agent Harnesses with Strands Agents course. This chapter covers model providers: how Strands abstracts the underlying LLM so your agent logic stays the same regardless of which model you're calling. We go through how to configure different providers (Amazon Bedrock, Anthropic, OpenAI, local/custom endpoints), how to switch between them with one line, and why this matters in practice. Maybe you prototype on a cheap fast model and deploy on a stronger one. Maybe you route simple queries to Nova Micro and complex ones to Sonnet. The provider abstraction is what makes that possible without rewriting your tools or your prompts. 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). Reference Reading Configuring Model Providers: https://go.aws/4vkbS1C Github Repo with Readings: https://go.aws/4aBev7K Strands Agents SDK: https://go.aws/4fo8bD9 Follow AWS Developers! 🆇 X: https://go.aws/4ypoQOm 💼 LinkedIn: https://go.aws/4aFGcwb #AWS #AgentHarness #StrandsAgents