"Do as I say, not as I do" applies hard with MCP. There's too much focus on the problems without a focus on a solution.

Multi-agent collaboration sounds like a good idea in theory, but you quickly realize the game of telephone the agents play with each other lead to unpredictable results.

I recently put Postman's AI companion to the test, let's talk about what I learned.

Every year I write some software to creatively distribute presents to my brother. I might have gone too far this year.

Finding the time to create and post on social media takes time and expertise I don't have. So I asked AI to do it for me.

How often do you generative AI to write your code? What about writing your tests? You might be doing it backwards.

With more and more options that abstract away writing code, what will we be doing in 5 years?