-
Pencils Down: DHH, Rust, and the Kodak Moment for Software Engineers
When the creator of Ruby on Rails declares 37signals 'pencils down' on handwritten code, something structural has shifted. A breakdown of DHH's Rails World 2026 keynote, the irony of Rust, Omarchy, and why p(bloom) > p(doom).
-
The Great Model Unbundling: How Antigravity and Multi-Agent Orchestration Ended My Claude Monopoly
Six months ago, Claude handled 98% of our AI engineering sessions. Today, it is under 15%. Here is the telemetry from 308 production sessions on how Antigravity, LivAgent, and a Git-backed shared brain ended our Claude monopoly.
-
Dnyankosh MCP: The Blueprint for Enterprise AI Infusion
Why enterprise AI adoption stalls at the “clever toy” stage, and how building an MCP gateway over deterministic, Git-backed institutional knowledge provides a blueprint for scalable AI infusion.
-
AI in QA: Maturity Curves, the Shared Brain, and the OpenTelemetry Blindspot
Insights from a closed-door boardroom roundtable on AI in QA with tier-1 financial institutions: the 4-level maturity curve, validation of the Shared Brain architecture, and why everyone is ignoring OpenTelemetry.
-
AI in Indian WealthTech & Micro-Lending: Beyond the Chatbot Hype
Conversational AI chatbots are the least interesting application of AI in finance. The real transformation in Indian credit and WealthTech is happening in back-office engines processing unstructured GST, banking, and underwriting data.
-
Deterministic AI: Why I Replaced Vector DBs with Git & Markdown
Vector search promises infinite semantic memory for AI agents, but in production it introduces non-determinism, context fragmentation, and opaque debugging. Here is why we switched our agent memory to Git and Markdown.
-
My Experience at the Entrepreneur Future Summit 2026, Pune
I attended the Entrepreneur Future Summit in Pune, diving into practical applications of AI, scalable frameworks, and insights from global founders. Here's a recap of the best sessions and networking highlights.
-
How I Built a Shared Brain for My AI Agents
The usual workarounds for AI memory are brittle. What I needed was a shared external memory that any agent could read and write. Here's how I built a two-layer memory architecture using GitHub and GitLab.
-
I Built an AI “Second Opinion” System for My Own Health—Here’s How It Works
I got tired of walking out of a doctor's appointment wondering if it was the right call. So I built an AI-powered personal health memory system to cross-reference prescriptions against global evidence-based medicine.
-
The Git-Backed Brain: Using a Repo as Shared Agent Memory
If you're using multiple AI agents to get work done, you quickly run into a context fragmentation problem. The solution isn't a complex vector database. It's a simple GitHub repository.