TL;DR: MIT’s new State of AI in Business 2025 should be read as a blurry mirror. It reflects real pain points in a handful of enterprises, but it is far from a complete picture of global adoption. The lesson isn’t that “AI doesn’t work,” but that most organizations are still struggling to cross the pilot-to-production … Continue reading The MIT GenAI Report: A Blurry Mirror, Not the State of Enterprise AI
Tag: Generative AI
Detailed Security and Enterprise Readiness Report: Cursor AI IDE
Prepared for: Enterprise AI Teams and AI/Security Leadership Based on: Publicly available information and Cursor's provided documentation from:https://www.cursor.com/security, https://trust.cursor.com/faq and https://trust.cursor.com/ Table of Contents Executive Summary Introduction to Cursor Core Security Architecture and Practices AI Request Processing and Data Handling Codebase Indexing: Functionality and Security Privacy Mode: Guarantees and Implementation Enterprise-Specific Features and Considerations Potential … Continue reading Detailed Security and Enterprise Readiness Report: Cursor AI IDE
Ship Code 10× Faster: Guide, Don’t Grind—With AI Coding Assistants
1. The Productivity Cliff We’re Ignoring ? In 2025, not pair‑programming with an AI coding companion is like scrolling through Google results page‑by‑page while everyone else fires off one‑sentence queries to an AI search assistant—it technically works, but you bleed hours that snowball into months of lost velocity every year. I learned this the hard way. My … Continue reading Ship Code 10× Faster: Guide, Don’t Grind—With AI Coding Assistants
Answer Your “Why” Before Building an AI Product
“People don’t buy what you do; they buy why you do it.”— Simon Sinek It's very common nowadays, to see teams chase every new coding assistant, chatbot, and AI agent—only to end up spinning in circles. So let's drill down here. When you let shiny tools dictate your roadmap, you muddle your product vision, lose … Continue reading Answer Your “Why” Before Building an AI Product
Building an AI 10-Q Analyzer: Part 3 | Evaluating Results and Insights using O1-mini -using 10Qs from Microsoft and Rigetti
Read Part 1 here. Read Part 2 here. In the dynamic world of financial analysis, the ability to swiftly and accurately interpret complex quarterly filings like the SEC’s Form 10-Q is invaluable. To address this need, I developed an AI-driven pipeline leveraging the Google/flan-t5-base model, Retrieval-Augmented Generation (RAG), and Named Entity Recognition (NER). Recently, I … Continue reading Building an AI 10-Q Analyzer: Part 3 | Evaluating Results and Insights using O1-mini -using 10Qs from Microsoft and Rigetti
Building an AI 10-Q Analyzer: Part 2 | Navigating the Pros and Cons of Structured Output from 10-Q Systems
Read Part 1 here. Introduction In the realm of financial analysis, structured data extraction from complex documents like SEC 10-Q filings can revolutionize how investors make decisions. The 10-Q Analyzer project leverages AI to automate this process, but like any technological solution, it comes with its own set of advantages, disadvantages, and challenges. This blog … Continue reading Building an AI 10-Q Analyzer: Part 2 | Navigating the Pros and Cons of Structured Output from 10-Q Systems
Understanding Production RAG Systems (Retrieval Augmented Generation)
1. What is RAG ? Retrieval Augmented Generation (RAG), is a method where you have a foundation model, and you have a library of personal documents – this can be unstructured data in any format. Now your goal is for answering some questions from your persona library of docs, with the help of LLM. Enter … Continue reading Understanding Production RAG Systems (Retrieval Augmented Generation)
Infinite Couch 