AWS and Strands enable building AI research assistants in 30 lines of code using the Strands Agents open source framework.

**What happened** — AWS published a tutorial showing how to build a fully functional AI research assistant using Strands Agents (an open source framework) and AWS services like Amazon Bedrock, requiring only 30 lines of code.

**How it works** — Strands Agents combine large language models (LLMs—AI systems that understand and generate text) with custom logic and APIs through Python code. Developers define an agent's behavior via prompt engineering and provide tools; the LLM handles autonomous reasoning and tool selection. The framework integrates with Amazon Bedrock, Anthropic, and OpenAI, and is already used in production by AWS services including Amazon Q and AWS Glue.

**So what** — The approach eliminates the need for specialized knowledge in natural language processing and distributed systems to build agentic AI applications (AI that can reason and act autonomously). Developers can create custom agents for research, analysis, and content generation without managing complex orchestration, conversation state, or custom agent logic by hand.

**Access** — Strands Agents is Apache-2.0 licensed open source software with active community contributions. Over 50 curated powers (packaged capabilities) are available for the Kiro IDE from AWS, partners, and the community.