AI and ML have evolved from complex mysteries few years back to everyday tools, driven by models like ChatGPT and Bard. ChatGPT and Bard made AI easier, but most are still basic because turning them profitable needs rare know-how mostly in big companies. It's not just about Language Models; AI's larger development faces this. Many … Continue reading Understanding AI/ML Systems In Production
How to Think About AI Systems in 2026
Why GenAI, Predictive Models, and Agents Need to Work Together I’ve been working in AI since well before the GenAI wave, and one thing that has become almost annoying in the last couple of years is how quickly every problem gets thrown at an LLM—with the expectation that it will magically solve everything. It won’t. … Continue reading How to Think About AI Systems in 2026
Why Do Multi-Agent LLM Systems Fail? Insights from Recent Research
As GEN AI evolves, multi-agent systems (MASs) are gaining traction, yet many remain at the PoC stage. So this is where research papers and surveys help. Over the weekend, I explored their failure points and found a fascinating study worth sharing. MASs promise enhanced collaboration and problem-solving, but ensuring consistent performance gains over single-agent frameworks … Continue reading Why Do Multi-Agent LLM Systems Fail? Insights from Recent Research
Optimizing RAG Systems: A Deep Dive into Chunking Strategies.
When it comes to today’s AI systems, especially in Generative AI, the main challenge isn’t just building a basic system with, say, 70% accuracy—it’s about pushing that system to over 90% and making it reliable for real-world production. Optimizing RAG (Retrieval-Augmented Generation) systems is essential for reaching this level. Effective chunking, one of the foundational … Continue reading Optimizing RAG Systems: A Deep Dive into Chunking Strategies.
GPU vs CPU: Understanding Their Differences and Benefits for AI Processing
A lot of the buzz is around GEN AI from the last couple of years. The focus on GPU has increased significantly. Building a good understanding of why we need each and when is essentially to build our foundational understanding. So let's dive in. We will start by looking at the theory of both, then … Continue reading GPU vs CPU: Understanding Their Differences and Benefits for AI Processing
RAG Components – 10,000 ft Level
When you look at GEN AI and specifically LLM's from a usage point of view, we have a few techniques to interact with LLM's. This depends on whether you need to interact with external data or just use LLMs for your different tasks. RAG is an important technique and widely adopted because it helps you … Continue reading RAG Components – 10,000 ft Level
Evaluation and Experiment Tracking for LLM’s
Have you ever done text generation with an LLM and though: I wish I could track experiments and evaluate different LLM results in terms of cost, sample comparison and memory together like below? If yes this article for you. Experimentation tracking is one critical piece of model development which is very important as it helps … Continue reading Evaluation and Experiment Tracking for LLM’s
Experimenting With Multi Model Rag and Google Gemini
In the world of LLM's, rag has gained quite a bit of traction due to the fact that it helps reduce hallucination by giving access to LLM's to external sources and grounding the results. In simple words, RAG is basically proving an external data source for Generative AI models to get better context on user … Continue reading Experimenting With Multi Model Rag and Google Gemini
Understanding RAG and Vector DB
For anyone in the field of AI and ML, they probably do know all of these terms. But how do you explain these to someone new. Let's try understanding this. USE CASE: Mark wants to plan a trip to Georgia in Europe and he wants to use an LLM for this. INTERACTION WITH LLM: Attempt … Continue reading Understanding RAG and Vector DB
AI Use Case Template – 30,000 ft
Over the last few years having worked on the production side of AI I have had the experience working with a few AI/ML initiatives. Some have made it to production and a lot have not made it to production. Failures happen at multiple stages :- Inception stage: idea proposed from products team and dropped for … Continue reading AI Use Case Template – 30,000 ft
ML Monitoring In Production- Why and What(30,000 ft)
Why to Monitor? What is the goal of an ML system for a business use case? Do you think it is below? i.e Designing an ML system which has the best model accuracy Not exactly. The goal looks more like below True ROI from an ML system is only achieved by monitoring the system in … Continue reading ML Monitoring In Production- Why and What(30,000 ft)
AI For Production 