Amazon Bedrock for Beginners – From First Prompt to AI Agent
A companion code repository for a beginner tutorial video and blog that builds a university FAQ chatbot on Amazon Bedrock step by step, from a first Converse API call through tool use, retrieval-augmented generation, guardrails, and a full agent built with the Strands Agents SDK.
This repository provides runnable Python examples that build up from a single Amazon Bedrock API call to a complete AI agent. Early examples cover the Converse API for a first model call, and a multi-turn conversation example that manually resends conversation history since Bedrock models are stateless between calls. A tool-use example defines a local function, describes it as a tool schema, and walks through the full loop of the model requesting a tool call, the code executing it, and the result being returned to the model.
Later examples require creating an actual Amazon Bedrock Knowledge Base in the AWS console, uploading FAQ documents to S3 and connecting them for retrieval-augmented generation, and add content-safety guardrails and a full agent that ties tool use, retrieval and conversation together with the Strands Agents SDK, resulting in a working university FAQ chatbot.
It requires Python 3.12 or later and an AWS account with an IAM role or user configured, and is licensed under MIT-0.