Cloud computing has become an important part of modern technology, and I recently started exploring AWS to understand cloud services. As a student, I want to move beyond theory and gain practical experience. I am learning about AWS Regions, Availability Zones, EC2, S3, IAM, and Lambda. My goal is to build small cloud-based projects and improve my AWS skills through hands-on learning.

Learn how to design a production-grade human-in-the-loop (HITL) review system that catches and corrects AI extraction errors before bad data flows downstream — with a practical architecture, key design decisions, and lessons from the field.

The path I'm following to build practical, job-ready skills in cloud data engineering

MTurk ৩০ সেপ্টেম্বর ২০২৬ বন্ধ হবে। Worker-এর পাওনা, Requester-এর HIT ও Ground Truth/A2I নির্ভরতা সরানোর পৃথক সময়সীমা জানুন।

Descubra o que é a certificação AWS Certified AI Practitioner (AIF-C01), o que estudar (Bedrock, SageMaker, RAG) e dicas valiosas para passar na prova.

api-change:datazone: GetSubscriptionGrant now returns materialized asset scope name for mapping Lake Formation data cell filters or Redshift views to subscription grants.; api-change:textract: Amazon A2I entered maintenance mode in July 2026 and now rejects StartHumanLoop requests from accounts…

Each year, organizations lose tens of billions of dollars...

Learn about Amazon Augmented AI (A2I), a service for augmenting AI application labeling with human review loops to boost confidence in datasets.

My first AWS project worked exactly as expected—but I struggled to explain how or why. This is what I learned about the gap between building something and truly understanding it.

How I carried out my first AWS practical task on IAM

Top Amazon Execs showcase AI and how it has helped them in their daily life, from day to day.

Learn how to build production-grade RAG applications using Amazon Bedrock Knowledge Bases with advanced techniques like query reformulation, multi-modal processing, and responsible AI guardrails.

Renaming dozens of files by hand is slow and error‑prone, especially when dealing with assignment submissions, photos, or logs. To address this, Bulk File Renamer was created as a Python command‑line tool that batch‑renames files with prefixes, suffixes, numbering, and a safe dry‑run preview. Kiro accelerated the journey from initial idea to a tested, production‑ready script by providing scaffolding, refinements, and debugging assistance.

This project involved building a complete document summarization application using the Amazon Bedrock Converse API and Streamlit. The goal was to design a system that can accept PDF documents, process the content using a large language model, and produce concise, accurate summaries according to user instructions. The assignment demonstrates practical integration of Amazon Bedrock into a real-world application, combining frontend, backend, and model orchestration in a single workflow.

Hosting a static website on AWS involves storing and delivering HTML, CSS, JavaScript, and image files directly from the cloud without requiring a backend server. The most common approach is using Amazon S3 (Simple Storage Service), which allows you to upload your static files and enable static website hosting. Combined with Amazon CloudFront (for global content delivery) and Route 53 (for domain management), AWS provides a fast, scalable, and cost-effective solution.

Cloud platforms are being used by businesses and startups more and more in the current digital era to scale operations, increase flexibility, and lower infrastructure expenses easily.

Amazon Augmented AI (Amazon A2I)を使ったことがありませんでしたので、チュートリアルをやってみました。 チュートリアル: Amazon A2I コンソールの使用を開始するに公開されている手順です。 準備 A2IはTextract向け、Rekognition向け、カスタムの3種類があって、チュートリアルではTextractとRekognitionそれぞれにサンプルの...

This post outlines a custom multilingual document extraction and content assessment framework using a combination of Anthropic’s Claude 3 on Amazon Bedrock and Amazon A2I to incorporate human-in-the-loop capabilities.