Cloud technology makes building and scaling applications quickly and flexibly easier than ever. But one of the biggest challenges organizations face is cost management. Controlling…

  In today’s world, AI is no longer the exclusive domain of data scientists or machine learning engineers. We are entering an era where anyone can harness AI to work smarter and faster—especially professionals responsible for infrastructure management or platform development. Among the most noteworthy tools in this revolution is AWS Bedrock, a new service from Amazon Web Services that lets you access top-tier generative AI models from multiple providers without having to manage the infrastructure yourself. This article explains what AWS Bedrock is, why it’s impressive, whom it suits best, and how it can benefit platform engineers like us. Additionally, we share a brief firsthand experience to help those who might be interested in experimenting with it.   What Is AWS Bedrock and Why Is It So Exciting?   In simple terms, AWS Bedrock is a service that lets you access world-class generative AI models from several major vendors with just a click. In other words, it serves as a “one-stop shop” for high-quality AI models sourced from various providers such as Anthropic (Claude), AI21 Labs, Stability AI, Meta (Llama), and Amazon Titan (AWS’s own model). Each model offers unique strengths—some excel at summarizing information, others at translation or even image generation. Moreover, you can interact with these models through a single, unified API. The key benefits of AWS Bedrock include:   ????️ No Infrastructure Hassles: Forget about setting up servers, tweaking GPUs, or managing auto-scaling—AWS handles it all. ???? Flexibility in Model Selection: If you fancy using Claude one day and want to try Llama the next, you can switch models without any vendor lock-in. ???? Seamless Integration: It works effortlessly through APIs or SDKs, making it easy to connect with Lambda, API Gateway, or your own custom applications. ???? Security and Compliance: Benefit from the robust security standards of AWS’s trusted infrastructure.   Beyond these fundamental advantages, AWS Bedrock comes with a suite of advanced features designed to prevent misinformation and ensure the accuracy and suitability of responses:   ???? Foundation Model APIs: Access various AI models from different providers through a unified API. ????️ Custom Model Fine-Tuning: Tailor select models to fit your specific use cases. ???? Agents for Bedrock: Create agents capable of utilizing a toolchain, executing chain-of-thought reasoning, or interfacing with external data sources such as DynamoDB or other external APIs. ???? Knowledge Bases: Allow models to reference data from S3 or RDS and respond to queries based on that information. ????️ Guardrails: Set safety boundaries—for instance, preventing the discussion of sensitive subjects or the provision of incorrect data. Getting Started with AI the Easy Way Using Amazon Titan on AWS Bedrock   After discussing the theory behind AWS Bedrock, it’s time to share a hands-on experience to illustrate just how accessible this tool is. In our trial, we opted to use an AI model directly from AWS—the lightweight and cost-effective “Amazon Titan – Nova Micro.” Note that this model is currently available only in the N. Virginia region (it has yet to be launched in Thailand).   Our Use Case We set up a scenario where Nova Micro was tasked with creating a list of subtasks needed for opening a Jira ticket. The goal was to kickstart tasks quickly and minimize repetitive work. Here’s how we prepared:   Prompt Example ????✨ prompt = “Create a detailed list of subtasks needed to complete this task include testing and document. Format the response as a list where each item starts with ‘- ‘ and includes a clear and text, actionable subtask only one. The number of items may vary, but do not exceed 10. items. Task: ” Task Message message = ‘Install Jeknins on AWS ec2′   Nova Micro, our little model, works faster than expected! Just by entering the prepared prompt, the model can generate tasks completely and accurately, ready for real-world use. For example, it can instantly open a Jira task without the need to waste time thinking it through repeatedly. What I really like is the Chat mode, which is both easy and convenient — no need to write code to give it a try. And if the answer from this model isn’t quite what we’re looking for, we can easily switch to other models available in Bedrock to get the answer that best matches our needs, ready to be used for further tasks.     In real working life, we see these models as becoming key assistants in enhancing work efficiency — especially when used in combination with automation systems. And when we talk about automation, we can’t skip the topic of coding, which allows us to instruct the models to perform tasks systematically on our behalf. So today, let’s try writing a simple piece of code to call AWS Bedrock via its API.    What’s really great is that we can view the API request format directly from the AWS Console under the Bedrock section. By simply selecting the model we want to use, the system will display a ready-to-use API example right away. This makes it much easier to start coding without having to flip through multiple documentation pages or guess the parameters on our own.     We chose to use Boto3 to experiment with calling a model via AWS Bedrock, and here are the results. It must be said — it was both simple and very convenient. You could say it opens the door to using AI in daily work without complexity. AWS Bedrock truly makes AI feel much more accessible and no longer something distant or difficult to approach.   It’s just the beginning… but a crucial first step in bringing AI into your workflow.   From our trial use of AWS Bedrock with a lightweight model like Amazon Titan – Nova Micro, we’ve seen that getting started with AI through Bedrock is incredibly simple and truly accessible. Even though this was just a basic use case, it clearly helped improve both speed and efficiency in our workflow — especially when combined with code through Boto3, which allows the results to be seamlessly integrated… Continue reading AWS Bedrock: An Innovative AI Tool That Empowers You to Create with Ease

generate by AI In today’s world, where AI is increasingly becoming a part of everyone’s daily life, it’s no surprise that the term “AI” is mentioned so often. These smart AIs help improve efficiency and save time on tasks. One of the most interesting tools right now is Amazon Q Developer, a Generative AI developed by AWS (Amazon Web Services), designed specifically to support developers. What is Amazon Q Developer?   Amazon Q Developer, or simply Amazon Q, is a generative AI tool developed by Amazon Web Services (AWS). It acts like an AI-powered code assistant, designed to make project development smoother and more efficient. You can easily integrate it with popular code editors like Visual Studio Code (VS Code) and JetBrains IDEs (such as IntelliJ or PyCharm) by installing a plugin in just a few simple steps. One important note: you’ll need an AWS Builder ID to log in using the Personal Profile mode, which is necessary to get Amazon Q Developer up and running on your machine. Amazon Q Developer offers several features to assist developers, such as: ???? Code Explanation: Simplifies complex code to make it easier to understand ???? Unit Test Generation: Automatically creates tests for your code ????️ Bug Detection & Fix: Identifies errors in your code and suggests fixes ???? Documentation Assistant: Helps generate or recommend documentation for your code ???? Code Refactoring: Improves your code structure without changing its logic ???? AI Chat: A chatbot that understands the context of your code for Q&A All of these features can be easily accessed by typing the / symbol in Amazon Q’s chat box or used inline within your IDE, making it quick and convenient to use while coding. After trying out Amazon Q, I found that it works like a quick and easy-to-understand knowledge source for AWS services. Whether it’s about IAM, VPC, or other services related to Platform Engineering, Amazon Q makes it all easily accessible. Additionally, Amazon Q makes coding much easier, whether it’s using the AWS SDK or writing Infrastructure as Code with Terraform. As a Platform Engineer, I was curious to see how a tool like Amazon Q, designed to assist developers, could be applied to platform-related tasks and how it could help in our work. In this post, I’ll share my hands-on experience with Amazon Q and how it performed in this context. Hands-On Experience: Amazon Q in Platform Engineering We needed to create a Proof of Concept (POC) to integrate Azure AD with Jenkins. The challenge was that we often had to delete and recreate machines multiple times, which led to wasted time reinstalling Jenkins and the required plugins each time. So, we wanted to see if Amazon Q could help generate an Ansible script to install Jenkins along with the specified plugin versions. This would allow for quick and efficient reinstallation whenever needed. How we Tested From our experience with AI Code Assistants, we knew that the best way to make tasks easier and more aligned with our needs was to write a markdown file to create a clear prompt. And this is the requirement-amazonq.md file, which specifies what we want Amazon Q to generate. 2. We used Amazon Q to generate code base on this file. Amazon Q not only generated code but also provided recommendations for running Ansible correctly. 3. We adjusted some parameters, such as the EC2 instance’s IP address, Jenkins version, and the plugin versions we wanted. After that, we tested running Ansible. How it all turned out In our first test, Ansible failed with an “Error: Unsupported parameters” which prevented us from completing the Jenkins installation (we were using the code generated by Amazon Q without making any changes yet). So we sent the error message to Amazon Q for troubleshooting and received a fix. After fixing code, we ran Ansible again but this time we encountered “unzip: command not found” error. Once again, we consulted Amazon Q, and it generated additional code to resolve this issue. After applying the changes, we ran Ansible again, and this time it worked successfully!  We were able to install Jenkins and plugins easily using Ansible script generated by Amazon Q. However, when we checked the results in Jenkins, we noticed something odd???? —why plugin version didn’t match the one we specified? Instead, it was the latest version. Although Ansible code included specifying plugin version, the result wasn’t as expected. So, we consulted Amazon Q again to review and update code. After making necessary adjustments, we ran Ansible once more and finally, everything worked perfectly as expected! ???? Amazon Q: An AI Role Beyond Just Assistance   After working with Amazon Q, it’s clear that it’s a powerful tool. It can generate initial code quickly, help adjust and refine code to match our goals, and provide valuable guidance throughout the process. Even more importantly, Amazon Q acts as a reliable partner in DevOps and platform work, helping to improve efficiency and effectiveness. The more detailed and clear we make our prompts, the better Amazon Q performs. Amazon Q isn’t just a code assistant—it’s an “AI partner” that helps us work faster and more efficiently. I hope this article helps you discover a new tool that we might see at the AWS Summit Bangkok 2025! If your organization is looking for a DevOps solution to automate processes, reduce costs, and drive sustainable growth, SCB TechX is here to help you achieve those goals. Contact us at https://forms.office.com/r/P14E9tNGFD  References: https://docs.aws.amazon.com/signin/latest/userguide/sign-in-aws_builder_id.html https://aws.amazon.com/q/developer/ https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/what-is.html