Home

How AI Agents Can Work with TeamCity

TL;DR: At some point, we crossed an interesting threshold. AI agents can now set up TeamCity build configurations and even full build chains, add build features, and configure parameters. This works because TeamCity documentation is structured and accessible through MCP…

IntelliJ IDEA 2026.2 EAP Is Open

The Early Access Program (EAP) for IntelliJ IDEA 2026.2 is now ongoing. The first EAP builds are already available in the Toolbox App, on the website, and as a snap for Ubuntu. As always, EAP builds are free to use…

FairLens AI: An Intelligent Dashboard for Automated Bias Auditing

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built FairLens AI is a premium, high-end SaaS platform designed for AI-powered bias auditing. I built this tool to help data scientists and researchers easily identify, quantify, and mitigate…

You just can’t miss this…

Docker with AI: A Practical Guide to Running LLMs, Agents and MCP Harsh Manvar Harsh Manvar Harsh Manvar Follow May 26 Docker with AI: A Practical Guide to Running LLMs, Agents and MCP #ai #docker #machinelearning #llm 1 reaction Comments Add Comment…

AI Metrics Decoded: From Parameters to TOPS

AI Metrics Decoded: The Numbers That Actually Matter in Production Why You Need to Know This (Before Your First Production Incident) Picture this: your team picks a 70B parameter model for a new feature. It runs great on your MacBook.…

Redis Essentials: Architecture, Caching, and Setup

Redis is often a misunderstood tool in the backend developer’s arsenal. While many view it simply as a “topic” to be covered in an hour, its role in modern system design is pivotal for building high-performance, scalable applications. This article…

The Hidden Features of Claude

Most people use Claude like a chatbot. Ask a question. Get an answer. Maybe generate some code or summarize a PDF. That’s it. But after spending more time with Claude, I realized most users are barely scratching the surface of…

Everbench: A document management system with Local Intelligence

This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built Everbench Everbench is a low-cost, efficient document research platform for those concerned about privacy. I’ve been working on a project I called Everknown. It…

I got tired of writing post-mortems — so I built RCAi for SREs

I’m an SRE at Sony Interactive Entertainment. After a week where my teammate had four incidents (and four RCAs), I built something for the blank-page problem after every outage. What RCAi does RCAi turns an incident timeline into a structured…

How We Built a Multi-Agent AI Documentation System (And What We Learned)

Last quarter at Zeppelin Labs, we shipped Orchestrator-15 — a multi-agent documentation generation platform that takes a codebase or idea spec and produces production-grade technical documentation using coordinated AI agents. This post covers the architecture, the mistakes, and the specific…

SimGemma: Democratizing STEM Education with Offline-First AI Simulations

Introduction Imagine a classroom in a remote village. There’s a blackboard, a few passionate teachers, and curious students. What’s missing? A high-end physics lab. Even more challenging? A stable internet connection. Physics is a subject that demands exploration. It’s hard…

Four Levels Of Customer Understanding

Many companies think they know fairly well what their users want and need, and how they make their decisions. Yet most of the time these are merely big assumptions and big hunches — with little real evidence to support them.…

What If AI Didn’t Need the Internet?

*How Gemma 4 Could Bring Powerful AI Closer to People, Not Just Servers For a long time, using powerful AI has felt a bit like borrowing someone else’s computer from far away. Every question, image, or request had to travel…