Explained: Model Context Protocol (MCP)

You open your editor and ask the AI assistant why last night's build failed. A few seconds later it has pulled the CI logs, found the failing test, opened the commit that broke it, and checked whether anyone already filed a ticket. You never pasted a single log line into the chat. Not long ago, that kind of reach had to be built by hand. Someone wrote code that taught this particular assistant to talk to this particular CI system, then did it… Read More

In Focus: The Data Center Backlash Becomes an Election Issue

Information in this post reflects publicly available sources as of August 19, 2026. A party asks an industry for a favor Political parties usually tell industries what to do. This week the direction reversed. On August 18 the National Republican Senatorial Committee sent a private memo, headlined around Ohio data center risk, to leading AI companies. Axios obtained it and published the following day. The memo argues that Democrats have made data ce… Read More

In Focus: The AI Case for Enterprise Architecture

Information in this post reflects publicly available sources as of July 12, 2026. For most of the last decade, the received wisdom about enterprise architecture was that it was in decline. Cloud dissolved its authority, agile teams routed around it, and "we don't do EA here" became a mild boast at engineering conferences. Then, over roughly the past eighteen months, the message inverted. EA is now being described across the industry… Read More

Explained: Agentic AI

It is 11:40 pm and a deploy is blocked by one failing test. You paste the stack trace into a chatbot. It suggests a fix. You copy the fix into your editor, rerun the suite, get a new error, and paste that back. Nine round trips later, the test finally passes. The model did the thinking, but you did everything else: running commands, reading output, deciding whether to keep going. Now picture the same night with a coding agent. You type one senten… Read More

In Focus: AI-DLC

Information in this post reflects publicly available sources as of June 30, 2026. A solutions architect stands in front of a room at re:Invent and says six engineers rebuilt a core piece of Amazon infrastructure in 76 days. The original estimate was 40 engineers and a full year. The slide stays up just long enough for the number to land, and then comes the methodology that supposedly made it possible. That methodology is AI-DLC , and the numbers at… Read More