TeamBrain: From Sales Handoff Chaos to a Living Project Brain Every software team knows this moment. The deal closes. The kickoff meeting happens. And suddenly engineering is left asking: “What was actually promised?” “Where are the real requirements?” “Why are there six spreadsheets and three decks?” This isn’t a tooling problem. It’s a handoff problem. TeamBrain was created to fix that — not by writing more documentation, but by changing how project knowledge is generated,

Learn, Teach, Master: Your Springboard into a Fulfilling Tech Career with Java Spring Boot The tech world is booming, and landing a...

The Repogenic Loop Put the story in the repo. Let the repo drive the work. Turn a raw Jira story into repo-aware engineering intent, execution, validation, evidence, and a stronger repository for the next feature. The Repogenic Loop makes the repository the working center of software delivery. Story → feature.md → Intent → Implement → Validate → Evidence → PR → Better Repo Why it matters Your team should not have to reinvent the engineering process for every feature. The repo

How to Create the Repogenic Loop Software teams already have a starting point for most features. Usually, it is a Jira story, Azure DevOps work item, ServiceNow request, backlog item, or some other form of business requirement. The problem is that those stories rarely contain enough engineering context to safely drive implementation on their own. That is where the Repogenic Loop begins. The basic idea is simple: Put the work request into the repo, let the repo turn it into en

H1: Morning Brief — September 20, 2026 Today’s three strongest opportunities line up unusually well with what you’ve been working through: the repo becoming an engineering control plane, governed intent-to-PR loops, and resisting unnecessary multi-agent complexity. The interesting part is that several major engineering organizations are independently moving toward those same architectural ideas. ——— H2: The Software Factory Is Real. But the Factory Needs a Specification. On A

For the Glory of the Repo There is a tendency in AI-assisted software development to keep adding more. More agents. More orchestration. More platforms. More automation. More infrastructure. But lately, I have been moving in the opposite direction. Back to the repo. Not because the repo is new. Because we have underestimated what it can become. The Repo Is Becoming the Engineering System A modern repository does not have to be just a place where source code lives. It can c

The Repogenic Loop: How Teams Can Start Intent-Driven Engineering Right Inside the Repo Software teams do not need a new platform, a massive agent framework, or a six-month transformation program to begin working differently with AI. They can start in the repo. That is the idea behind what I call The Repogenic Loop. The concept is simple: The repository should not only contain the code. It should contain the intent, standards, architecture, reusable skills, templates, validat

# You Don’t Need Permission to Start: Building Portable AI Automation with Intent Files One of the lessons I keep learning with enterprise AI is simple: **The ideal architecture is not always the architecture you are allowed to use.** You may know exactly how you would like to implement AI-assisted developer automation. GitHub Copilot has repository-level customization, including `.github/copilot-instructions.md`, `.github/prompts/*.prompt.md`, path-specific instructions and

When AI Writes the Code, Architecture Becomes the Job Morning Brief — September 18, 2026 The software industry spent decades treating code as the center of gravity. Requirements became designs. Designs became code. Code was tested, deployed, maintained, and eventually replaced. That model is beginning to invert. AI can now produce a growing portion of the implementation. The scarce resource shifts away from typing code and toward specifying what should exist, constraining how

8 AI-Native Application Reference Patterns to Watch AI application development is moving fast. Too fast, in fact, to pretend that anybody has everything figured out. We are still in the Learn → Teach → Master stage of this shift. We are learning which application architectures work, teaching what we see working, and gradually moving toward mastery through repetition, evidence, and real production experience. That is why I prefer the term: AI-Native Application Reference Patte

Intent-Driven Engineering on YouTube Intent-Driven Engineering is now on YouTube. The Intent-Driven Engineering video series explores how artificial intelligence is changing software engineering, AI agents, software factories, developer workflows, repositories, MCP, reusable AI skills, Progressive Intent, architecture, testing, and engineering automation. If you are searching for Intent-Driven Engineering, AI software engineering, AI software factories, or practical ways to b

Intent-Driven Engineering is expanding. Over the past year, I’ve been writing, building, testing, teaching, and challenging some of the assumptions around how software engineering changes when AI becomes part of the development team. Now I’m taking that conversation to video. The new Intent-Driven Engineering video series is designed to be short, practical, opinionated, and focused on one question: Where is software engineering really going next? This isn’t about chasing ever

Intent-Driven Engineering: Building Software From Intent, Not Just Prompts Software development is changing faster than most organizations realize. For years, we built software by translating business requirements into specifications, specifications into tickets, tickets into code, and code into production. Generative AI accelerated pieces of that process. But it did not fundamentally change the process. Intent-Driven Engineering does. Intent-Driven Engineering starts with wh

Does Every AI Feature Need a Harness? No. But It Probably Needs Guardrails. I hear this question constantly from developers and engineers: “Where is the harness?” It is a fair question. As AI engineering matures, we are hearing more about AI harnesses, agentic workflows, orchestrators, subagents, MCP servers, structured schemas, tools, hooks, memory, observability, and autonomous loops. All of those things have value. But there is a danger in turning them into requirements fo

Want to Pass the Claude Architect Exam? Start With an Intent, Not a Study Guide Most exam preparation is static. You read the guide. You memorize terminology. You take a few sample questions. Then you hope the real exam asks the same kinds of things. AI gives us a much better way to learn. Instead of reading another 50-page study guide, I created a single adaptive exam intent that you can paste into your AI system and immediately start practicing for the Claude Certified A

AI Engineering Is Getting More Complicated While Developers Are Getting Less Productive Every few months, software engineering gets another new AI discipline. First, we had prompt engineering. Then vibe coding. Then context engineering. Then agents. Then MCP servers. Then skills, hooks, subagents, orchestration, evaluations, observability, structured outputs, and governance. I have spent the last several years working on Intent-Driven Engineering, trying to bring some structu

Progressive Intent: I Built This Working Application in About Three Hours I’ve written quite a bit lately about Progressive Intent and Intent-Driven Engineering. So instead of explaining it again, I decided to give you the whole thing. The application is live. The source code is public. The intent files are in the repository. You can play with it, download it, fork it, break it, improve it, or use the approach on something completely different. And the interesting part? I bui

# Approved MCP Servers — Registry & Governance ## Why this document exists Connecting to an MCP server is easy — that’s the point of the protocol. A developer gets a URL (and maybe a header), points a client at it, calls `list_tools()`, and starts calling capabilities. No new SDK, no bespoke auth flow, no custom response parsing to learn per system. That ease is exactly why this document matters. The protocol standardizes *how* you connect. It says nothing about *what you’re

Your Company Does Not Have AI Automation. It Has Employees Prompting AI. Companies everywhere are reporting impressive AI productivity gains. Developers are using GitHub Copilot to generate code. Analysts are using ChatGPT to summarize documents. Teams are using Gemini to research problems. Engineers are asking Claude to interpret legacy systems, generate tests, refactor code, troubleshoot failures, and create documentation. And employees are reporting that they save hours. T

Three Layers of AI-Native Engineering: A Practical Framework for the Consulting Architect When you move from client to client as a consultant, AI architect, or enterprise architect, one lesson becomes obvious very quickly: You rarely get to choose the starting point. Every company is different. One organization may have mature cloud platforms, centralized APIs, shared services, AI governance, and established engineering standards. Another may have strong feature teams but ver