Hello Reader, Another week, another AI announcement. But this one is worth studying because this one will become the defacto standard of running agents on AWS. I am talking about newly released Amazon AgentCore. Let's dive in. 🧩 The Big Picture: Why Agents Exist Let’s break it down using a practical example: What happens when a user asks an LLM app: What’s the time in New York? What’s the weather there? List my S3 buckets The LLM don't have these information, hence it needs to invoke tools...
6 days ago • 4 min read
Hello Reader, Often I hear this - API Gateway is Serverless, hence it's better than Application Load Balancer (ALB). In todays newsletter edition, we will take an objective look at both, consider pros and cons, and more importantly how to tackle this in system design or tech interview. Remember our guiding principle - to get the job, or to excel at the job - you need to DELIGHT and not just MEET the standard. Let's get started. Both can route traffic to backends, both are managed by AWS, and...
13 days ago • 3 min read
Hello Reader, AI agent frameworks have created a crowded and confusing landscape. This edition offers a direct, value-focused comparison of these popular frameworks, examining their features, ease of use, enterprise readiness, and ideal use cases to help you decide which is best suited for your project. This edition of the newsletter is written by Adam Bluhm, Principal AI Engineer at HiddenLayer, and a former award-winning Senior Solutions Architect at AWS. Adam Bluhm builds and architects...
20 days ago • 6 min read
Hello Reader, In today's newsletter, I am going to share three tips that helped me and many of my students switch careers to the cloud and get high-paying jobs. I will also share an update about the upcoming Sep cohort of the AWS SA Bootcamp. Tip 1: Leverage your IT experience Your existing IT experience is NOT throwaway. Don't think you can't reuse components of your existing knowledge in your cloud journey. For example, my mentee and SA Bootcamper Rukmani, came from software engineering...
about 1 month ago • 4 min read
Hello Reader, In today’s post, let’s look at another correct but average answer and a great answer that gets you hired for common cloud interview questions. And this ties to a larger thread - most candidates fail their Solutions Architect interviews - not because they’re underqualified… But because they don’t know how to communicate like a Solutions Architect. How to stand out as a must-hire? Let's start with a common question, and we will go from there! Question - What's the difference...
about 2 months ago • 3 min read
Hello Reader, Not all questions are equal in interviews and real-world projects. There are some questions that you simply can't mess up, because these concepts are so fundamental, they are used in almost ALL projects. One such concept is high availability. Surprisingly, I hear wrong answers on this all the time. In this edition, let's go over the common bad answers, a good answer, and then some! Question: What is High Availability? Bad Answers Even if a component fails, application should...
about 2 months ago • 1 min read
Hello Reader, EDA (Event Driven Architecture) has become increasingly popular in recent times. In this newsletter edition, we will explore what EDA is, what the benefits of EDA are, and then some advanced patterns of EDA, including with Kubernetes! Let's get started: An event-driven architecture decouples the producer and processor. In this example producer (human) invokes an API, and send information in JSON payload. API Gateway puts it into an event store (SQS), and the processor (Lambda)...
2 months ago • 3 min read
Hello Reader, In today’s post, let’s look at another correct but average answer and a great answer that gets you hired to common cloud interview questions. Question - What is RTO and RPO? Common mistakes candidate make - they say RPO (Recovery Point Objective) is measured in unit of data, e.g. gigabyte, petabyte etc. Here is the right answer - Both RPO and RTO are measured in time. RTO stands for Recovery Time Objective and is a measure of how quickly after an outage an application must be...
2 months ago • 1 min read
Hello Reader, Most engineers are using MCP clients and agents. But very few know how to build and host an MCP server, let alone run it remotely on the cloud. In today's edition, we will learn how to create and run a remote MCP server on Kubernetes, on Amazon EKS! I will share the code repo as well, so you can try this out yourself. But first.. 🔧 What is an MCP Server really? It’s not just an API that performs a task. An MCP Server is a protocol-compliant endpoint (defined by Anthropic) that...
3 months ago • 2 min read
Hello Reader, On my interactions, this question is coming up a lot - “How are AWS Strands different from Bedrock Agents?”. In today's newsletter, we will go over this, so you can also answer this in your interviews or real-world projects Let’s break it down using a practical example: What happens when a user asks an LLM app: What’s the time in New York? What’s the weather there? List my S3 buckets The LLM don't have these information, hence it needs to invoke tools for time, weather, and AWS...
3 months ago • 2 min read