Post by Rajdeep Saha

What is the difference between Bedrock Agents, Strands Agents, and Bedrock Agentcore? Think of AWS Strands as a single Python program that can implement powerful agentic workflows with a minimum amount of code. - Supports both Bedrock and external LLMs (e.g., Anthropic Claude) - This one is awesome - it comes with 20+ prebuilt tools, that you do NOT have to code. For example:current_time (gives current time), use_aws (uses boto3 under the hood to list AWS resources), http_request (figures out API calls automatically) - You can create your own custom tool - It has MCP client built in, allowing you to connect with MCP Servers At this point, you have your agent running in your laptop. Amazon Bedrock Agentcore helps you run this agent on AWS! - Run command "agentcore configure" and it will create a DOCKERFILE to containerize your agent code - Run command "agentcore launch" and it will upload and run your agent from local to Agentcore in AWS! - The underlying infra is Serverless - Logs, metrics, traces are automatically configured and provided - AuthN/Z can be added easily Ohh, and Bedrock Agents - you have to code separate Lambdas for each tool. With Strands + Agentcore it's safe to say, I ain't touching Bedrock Agents anymore! ---- Get byte sized tips on career switch, cloud, AI, system design, behavioral, and interviews in weekly newsletter (FREE) : https://lnkd.in/eG7XdHmN