If you are already familiar with the AWS landscape and want to get started with Agentic AI – look no further. Get started with Amazon Bedrock Agents. It’ll be way easier than you learning a completely new framework. This is of course NOT paid endorsement. I just want more people to get their hands dirty with Agentic AI rather than stand by and be a spectator saying to themselves “If only I knew Python”. What is Bedrock Agents? Bedrock Agents is an AWS-stack specific way of building out Agents and Workflows. Below is a diagram that we usually use to…

Vector Databases have become popular with the advent of GenAI. And rightfully so. They are a useful tool for “Context Engineering” for GenAI applications particularly for RAG (which deals with a lot of unstructured data). But they are also slightly difficult to comprehend. We live and breathe in a 3D world. Hence, it’s difficult for any person to fully grasp say a 1024-dimension vector collection. Solution? Instead of moving towards hyperdimensions let’s move 1 dimension down. Let’s consider a 2D plane. Nothing fancy – just consider a blank rectangular table top. Now, consider that we have a stack of animal…

Tell me if this sounds familiar. You want to get more familiar with GenAI. You start to read an article or watch a video. But soon you start drowning in the quicksand of unnecessary theory, fragmented tutorials and multiple pathways. It’s not your fault. The waters of GenAI are muddled with too many confusing options. I’ve witnessed countless talented individuals get trapped in this maze, spending months consuming content fruitlessly. They end up building neither anything substantial to showcase nor their confidence. Valuable time and effort both wasted in the wrong pursuits. Ouch! Some learners get advised to fully comprehend…

Goal On this page you will find simple guidance on which Agentic AI Framework to start learning. Advice If you are already fluent in a programming language, pick a framework available in your language. That’s it. Eliminate all of the other options from the selection board. Make it easier for yourself by choosing a framework in the language whose basics you already know. That will cut down your learning effort and time. If you don’t know how to code, best to pick a low-code or no-code framework. Alternatively, you could learn the basics of Python and augment yourself with a…

Challenges Some of the common problems that stand in the way of ramping up on GenAI knowledge are Here are some of the “remediations” for the above objections. Hopefully the common objections are addressed by now. Let’s move on to the guidance portion now. Avoid learning Learn to operate at a level of abstraction. There is NO need to learn the following topics unless you are applying for a role where you need to build LLMs from scratch. As an analogy, when you go to a motor driving school, the driving instructor does NOT teach you how an Internal Combustion…

Agentic AI is the buzzword of the season. And for all the right reasons. But 2 serious drawbacks of Agentic AI are high costs and slow speed due to the usage of reasoning models for crafting a plan for agent invocation (and tool usage) and multi-step LLM calls for finally arriving at the end goal. Model Distillation is a very well placed offering made GA by the hard working team at Amazon just few days ago. What is Model Distillation, eh? Model distillation involves transferring knowledge from a larger, more capable “teacher” model to a smaller “student” model. This process…

Agentic AI is the buzzword of the season. My team and I’ve been solving customer problems using Agentic AI solutions for a while and here are some observations and predictions. Terminology To make it easier to converse related to Agentic AI solutions, we would need to speak the same language. Terms like ReAct, Self-critique, LLM-as-a-judge will become part of our vocabulary. The previous wave of LLM adoptions already achieved this with terms like RAG, CoT & Reasoning. We might see add-ons to the overall design language. This will be similar to how we don’t use a plain rectangle to represent…

In the last couple of years, Generative AI (Gen AI) has swiftly made its mark in software engineering, infiltrating the daily workflows of developers, testers, and managers alike. But before we dive into today’s AI-fueled reality, let’s rewind a few years. Back then, everything was mostly manual, and, things were running just fine! Developers were coding, testers were testing, and project managers? Well, they were juggling all the chaos like seasoned pros. So, why Gen AI now? Were developers suddenly unable to write code? Did testers forget how to break software (in the best way possible)? Did managers lose track…