DEV Community: Bhuvanesh A

☁️AWS Rhyming Game Contest Using Amazon Bedrock

Bhuvanesh A — Tue, 15 Sep 2026 15:00:54 +0000

Introduction

As part of the Rhyming Game Contest, I had to select an AWS service that starts with the first letter of my name. Since my name is Bhuvanesh, I selected Amazon Bedrock, an AWS service that starts with the letter B.

Artificial Intelligence has become an important part of modern applications. However, developing generative AI applications from scratch can require large amounts of computing resources, machine learning knowledge, and infrastructure. AWS created Amazon Bedrock to make it easier for developers to use powerful foundation models (FMs) and build generative AI applications without having to manage the underlying infrastructure themselves.

Amazon Bedrock is a fully managed AWS service that provides access to foundation models from different AI model providers through a common platform. Developers can use these models for tasks such as text generation, summarization, question answering, content generation, and building AI assistants.

What is Amazon Bedrock?

Amazon Bedrock is a fully managed generative AI service provided by Amazon Web Services (AWS).

Instead of training a large AI model from the beginning, a developer can select a suitable foundation model available through Bedrock and send it a prompt. The model processes the prompt and generates a response.

For example, a student could provide:

"Explain cloud computing to a first-year student."

The selected foundation model can then generate a simple explanation.

This makes Bedrock useful for students and developers who want to experiment with generative AI without building and maintaining large AI infrastructure.

Why Was Amazon Bedrock Created?

Building a large foundation model requires significant amounts of data, computing power, time, and expertise. It is not practical for every organization or student project to train such models from scratch.

Amazon Bedrock was created to provide easier access to foundation models through AWS. It allows developers to focus more on building applications rather than managing model infrastructure.

It can also be useful when organizations want to experiment with different foundation models and integrate generative AI into their existing applications.

How Amazon Bedrock Works

The basic workflow can be understood in a few simple steps:

The user creates an application.
The application sends a prompt to Amazon Bedrock.
Bedrock sends the request to the selected foundation model.
The model processes the prompt.
The generated response is returned to the application.
The application displays the result to the user.

Key Features

1. Access to Foundation Models

One of the major features of Amazon Bedrock is access to different foundation models through a single AWS service.

This gives developers flexibility when selecting a model based on their application requirements, such as response quality, speed, or cost.

2. Model Customization

Bedrock provides options for adapting models for specific applications. Depending on the model and feature being used, developers can customize the behavior of models using techniques such as fine-tuning or other supported customization methods.

This can help an application produce responses that are better suited to a particular domain.

3. Knowledge Bases and RAG

Amazon Bedrock supports Knowledge Bases, which can be used to build Retrieval-Augmented Generation (RAG) applications.

Instead of relying only on the information contained in the foundation model, an application can retrieve relevant information from an organization's documents or knowledge sources and use it to generate a response.

For example, a college chatbot could retrieve information from college regulations, department documents, or course materials before answering a student's question.

4. Agents

Amazon Bedrock also provides capabilities for building AI agents.

An agent can be designed to understand a user's request and interact with supported tools or data sources to complete a task. This can be useful when an AI application needs to do more than simply generate text.

5. Security and AWS Integration

Because Bedrock is an AWS service, it can be integrated with AWS security and identity services such as AWS Identity and Access Management (IAM).

This allows organizations to control who can access resources and services.

College / Student Use Case 🎓

A practical use case for Amazon Bedrock in a college environment is a Department AI Assistant.

Suppose an AIML department has information about:

Course subjects
Laboratory schedules
Faculty information
Department announcements
Project guidelines
Examination information
Frequently asked questions

A student could ask:

"When is the Advanced Machine Learning Lab?"

The AI assistant could retrieve the relevant information from the department's knowledge base and provide an answer.

A RAG-based architecture could look like this:

Student
   │
   ▼
College AI Assistant
   │
   ▼
Amazon Bedrock
   │
   ▼
Knowledge Base
   │
   ▼
College Documents
   │
   ▼
Relevant Information
   │
   ▼
AI Generated Answer

This could reduce the time students spend searching through multiple documents.

Simple Practical Example

A simple Bedrock application can send a prompt to a foundation model and receive a generated response.

For example, the application could send:

Prompt:
"Give me five words that rhyme with 'cloud'."

A possible response could be:

Loud
Proud
Crowd
Allowed
Shroud

This connects directly with the Rhyming Game Contest.

A simplified application flow is:

Python Application
       │
       ▼
Amazon Bedrock API
       │
       ▼
Foundation Model
       │
       ▼
Generated Rhyming Words
       │
       ▼
Display Result

In an actual application, AWS SDKs such as Boto3 can be used from Python to communicate with AWS services. The exact API code depends on the selected Bedrock model and AWS configuration.

Advantages

Easy Access to Generative AI

Developers can use foundation models without building large AI infrastructure from scratch.

Flexible Model Selection

Developers can choose from supported foundation models based on their application requirements.

Scalable

Bedrock is a managed AWS service and can support applications that grow from experimentation to larger workloads.

Integration with AWS

It can work with other AWS services and security mechanisms, making it suitable for cloud-based applications.

Useful for Student Projects

Students can use Bedrock to experiment with chatbots, AI assistants, document question-answering systems, content generation, and other generative AI applications.

Limitations / Things to Consider

Cost

Amazon Bedrock is a paid AWS service. Costs depend on the features and models used and, for applicable models, the amount of input and output processed. Students should monitor their AWS usage and understand the pricing before running large experiments.

Model Availability

The availability of specific foundation models and features can depend on the AWS Region and current AWS offerings.

Complexity

Although Bedrock removes much of the infrastructure management, beginners still need to understand concepts such as IAM permissions, AWS Regions, APIs, prompts, and model selection.

Security

Applications should avoid exposing sensitive information through prompts or application interfaces. Proper IAM permissions and AWS security practices should be followed.

Output Quality

Generative AI models can sometimes produce incorrect or unexpected responses. Important information should therefore be verified rather than blindly accepting generated content.

Conclusion

Amazon Bedrock provides a convenient way to build generative AI applications using foundation models through AWS. Instead of training and managing a large AI model from scratch, developers can focus on creating applications that solve real problems.

For students, Bedrock can be particularly interesting because it can be used to create AI assistants, educational applications, document-based question-answering systems, chatbots, and other innovative projects.

For my B challenge in the Rhyming Game Contest, Bhuvanesh meets Bedrock. The service demonstrates how cloud computing and generative AI can be combined to create practical applications with relatively less infrastructure management.

References

AWS Documentation – Amazon Bedrock
AWS Documentation – Amazon Bedrock User Guide
AWS Documentation – Amazon Bedrock Knowledge Bases
AWS Documentation – Amazon Bedrock Agents
AWS Documentation – AWS Identity and Access Management (IAM)

Official AWS documentation:

https://docs.aws.amazon.com/bedrock/

https://aws.amazon.com/bedrock/

🚀 From Localhost to the Cloud: Deploying My Portfolio with AWS S3 & CloudFront

Bhuvanesh A — Tue, 15 Sep 2026 07:01:37 +0000

My Hands-On Experience with AWS Cloud-Native Systems

I recently attended a workshop on Cloud-Native Systems & Applied AI Integration, where I got an introduction to AWS and several important cloud computing concepts.

Introduction to AWS

We started with AWS (Amazon Web Services) and its pay-as-you-go pricing model, where users pay based on the resources they use.

We also discussed the "Pizza as a Service" model to understand different levels of cloud services:

Traditional On-Premises
IaaS — Infrastructure as a Service
CaaS — Container as a Service
PaaS — Platform as a Service
FaaS — Function as a Service
SaaS — Software as a Service
AIaaS — AI as a Service

This helped me understand how responsibilities are divided between the user and the cloud provider across different service models.

Session 1: EC2, S3 and Networking

The first session covered some of the fundamental AWS services and networking concepts.

IAM

We learned about IAM (Identity and Access Management), which is used to manage users, permissions, and access to AWS resources.

Regions and Availability Zones

AWS infrastructure is organized into Regions, which contain multiple Availability Zones (AZs). This architecture helps provide high availability and fault tolerance.

Amazon S3

We explored Amazon S3 (Simple Storage Service) and its use for storing and hosting static objects such as website files.

Some important concepts we covered were:

Bucket: A container used to store objects. S3 bucket names must be globally unique.

High Availability: S3 is designed to provide highly durable and available storage.

ACL: Access Control Lists can be used to control access to S3 resources.

Bucket Policy: A policy used to define access permissions for objects within an S3 bucket.

We also learned about Amazon CloudFront, which is a Content Delivery Network (CDN) that can distribute content from an origin such as S3.

Hands-On: Deploying My Portfolio

For the practical session, I used my portfolio website, which was contained entirely in a single index.html file.

I created an S3 bucket, uploaded my index.html, configured the bucket for static website hosting, and accessed my portfolio through the S3 website endpoint.

We then attempted to configure CloudFront with the S3 bucket as the origin. However, AWS required my account to be verified before I could create a new CloudFront resource, so I could not complete that part during the workshop.

We also explored AWS Cloud Quest, which provided an interactive way to learn and practice AWS concepts.

Key Takeaways

This workshop gave me practical exposure to cloud deployment and helped me understand how services such as IAM, EC2, S3, networking, and CloudFront fit together in a cloud environment.

The hands-on deployment of my own portfolio using S3 was particularly useful because it allowed me to see the process of taking a local index.html file and making it accessible through AWS.

Although I could not complete the CloudFront deployment because of the account verification issue, troubleshooting the error was also a valuable part of the learning experience.

Technologies: AWS S3, AWS CloudFront, EC2, IAM, HTML, Static Website Hosting

Workshop: Cloud-Native Systems & Applied AI Integration
Coimbatore Institute of Technology | September 15–16, 2026