Chunking Is Where RAG Silently Fails
You have tuned everything. A better embedding model, a reranker, hybrid search. Retrieval quality is still not what it should be, and you cannot…
Archive
Author: Aakash Sharan
posts
102
Building Production-Ready LangChain Agents: Architectural Patterns That Work
Turning architectural gaps into engineering patterns The Gap Between Demo and Production Last week I evaluated LangChain's architecture using SRAL. The scorecard revealed something…
Research Vault: Open Source Agentic AI Research Assistant
The Problem Nobody Talks About I was drowning in research papers. Not metaphorically—I had 50+ PDFs, dozens of articles, and a note-taking system that…
Applying SRAL to LangChain: An Architectural Evaluation
A systematic evaluation of LangChain's architectural foundations using the SRAL framework Scorecard Summary Component Score Key Finding State ⚠️ Weak-to-Moderate Memory is optional, not…
Tools Don’t Extend an Agent. They Define It.
A 6.7-billion-parameter model, given a handful of tools, beat a model 26 times its size on a range of zero-shot tasks, from factual lookups…
SRAL Framework: The Four Questions I Ask About Every AI Agent
The Problem With Agent Evaluation Most conversations about AI agents focus on capabilities. Can it browse the web? Can it write code? Can it…
PART II — ReAct: The Architecture That Unified Agentic Reasoning
Most discussions of ReAct frame it as a clever prompting technique. It isn’t. ReAct is the first time we gave language models a structure…
Rising CAC Is a Symptom, Not the Disease
A survey of more than a hundred Indian D2C founders this year surfaced a number that looks like a marketing problem and is actually…
Machine Learning Types Are the Wrong Abstraction for Agentic Systems
Executive Summary We still classify machine learning systems by how they are trained. Supervised. Unsupervised. Reinforcement learning. That taxonomy made sense when models were…
Statistics: Why Intelligent Systems Must Admit Uncertainty
Executive Summary Most intelligent systems don’t fail because they lack data. They fail because they treat estimates as facts. Statistics exists to solve a…