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...

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

Claude Certified Architect Foundations: A Practical Architecture Guide for Test Takers If you are preparing for the Claude Certified Architect Foundations exam and you already have years of software, cloud, integration, or enterprise architecture experience, one thing may surprise you: The exam can feel much lower-level than the word architect suggests. You may find yourself answering questions about Glob, Grep, Read, CLAUDE.md, Hooks, Skills, MCP configuration, JSON schemas,

If I Were a Software Engineer With “Open to Work” on LinkedIn, I’d Be Learning to Work Like a Forward Deployed Engineer There are a lot of very good software engineers looking for work right now. Some have ten years of experience. Some have twenty. They know Java, .NET, Python, JavaScript, React, AWS, Azure, databases, APIs, microservices and CI/CD. And many of them are still waiting. If I were one of them, I would ask myself a difficult question: Am I marketing myself for th

Progressive Intent: A Simpler Way to Build Better Software With AI For the last several years, much of the conversation around AI-assisted software engineering has been driven by the biggest companies in the world. That makes sense. https://github.com/kendallmark3/whackamole Large enterprises have enormous engineering organizations, thousands of repositories, complex security requirements, multiple layers of governance, global delivery teams, compliance obligations, shared pl

Progressive Intent: A Simpler Way to Build Better Software with AI There is a growing tendency in AI-assisted software development to add more architecture before we have proven that we need it. Skills. Agents. Sub-agents. Hooks. Orchestrators. Tool chains. Context layers. Observability. Shared services. All of those things can be valuable. But I have been exploring a much simpler question: What if a good intent file is already enough to get most of the way there? That questi

The Intent-Driven Playbook A practical starting point for teams that want to move from prompting AI to engineering with intent Most teams do not need another AI framework. They need a way to start. They need a structure that is simple enough to use immediately, but strong enough to scale into real engineering. They need to know what belongs in the request, what context the AI should receive, when to use agents, when to use automation, how to validate the work, and how to get

The Next Operating Model for Software Engineering For most of the software industry’s history, engineering productivity has been constrained by human throughput. Ideas had to be translated into requirements. Requirements had to be translated into designs. Designs had to be translated into code. Code had to be tested, reviewed, deployed, monitored, and maintained. Every transition introduced delay, interpretation, and loss of intent. Generative AI is beginning to change that e

Every Repo Team Should Be Automating Its Own Work AI adoption inside an enterprise does not have to begin with a massive platform. It does not have to begin with a global architecture. It does not have to begin with an enterprise-wide transformation program. Sometimes it should begin with five engineers looking at their own repository and asking a very simple question: What are we doing manually today that this team should never have to do manually again? That is where I beli

Intent-Driven Engineering, Revisited: The Industry Is Starting to Converge For a long time, I have been writing about Intent-Driven Engineering. Intent files. Context. Skills. Hooks. Agents. Tools. MCP. Contracts. Structured inputs and outputs. Validation. Governance. Orchestration. At times, it probably sounded like a growing collection of AI terminology. It isn’t. After going around this problem again and again—building systems, watching the platforms evolve, seeing what wo

Stop Building AI Infrastructure. Just Structure the Handoffs. You Probably Don’t Need a Contract Engine, State Machine, or Global Messaging Platform There is a point in almost every architecture discussion where a simple engineering principle starts turning into a platform. Structured agent output is heading in that direction. We start with a reasonable idea: When one intelligent component hands work to another, make the handoff predictable. Then suddenly we’re discussing glo

Stop Teaching the AI. Teach the Repository. Claude Code Has Skills, Agents and Hooks. So Does the Pattern. Something interesting is happening in AI-assisted software engineering. Developers keep asking: Which AI should we standardize on? Claude Code? GitHub Copilot? Cursor? Gemini? Something that hasn’t been released yet? I think that’s increasingly the wrong question. A better question is: How do we engineer a repository so that an AI coding agent understands how work is sup

We Don’t Bet on One AI. We Bet on Engineering. The Learn · Teach · Master Approach to AI Engineering Every few months, the technology industry gives us another reason to believe we have finally discovered THE way to build software with AI. A new model arrives. A new coding environment gets better. Agents become more capable. Skills appear. Hooks appear. MCP expands. Context engineering becomes a discipline. Orchestration frameworks multiply. Claude. GitHub Copilot. Cursor. Ge

Yes. The architecture pattern is portable, but the exact names, file formats, trigger semantics, and maturity differ by platform. GitHub Copilot is especially close now: its current docs explicitly describe custom agents, automatically selected subagents, automatically selected skills, deterministic lifecycle hooks, MCP servers, and orchestration. Stop Thinking About AI Features. Start Thinking About What Fires Them. Agents, Skills, Hooks, Tools and Workflows Finally Started

Everyone Has “THE Way” to Build AI Now — Maybe That’s the Wrong Way to Think About It Spend five minutes on LinkedIn today and you can find the new way to build software with AI: Agent Engineering. Context Engineering. Harness Engineering. Flow Engineering. Spec-Driven Development. Agentic Engineering. And, yes, Intent-Driven Engineering. At first, this looks like another technology-industry naming contest. But beneath the terminology, serious practitioners are converging on