I wanted to build a playlist around a specific vibe but couldn’t quite name it. Songs like Kurt Vile’s “Check Baby” and Mark Lanegan’s “Hit the City” captured that laid-back, unhurried confidence. Not slacker enough to be lazy, not energetic enough to be aggressive. Just effortlessly cool. Searching by genre or artist wasn’t cutting it. The usual categories were too broad, too vague. So I decided to use AI to help me find every song in my 2,500-plus track library that fit this aesthetic.

Last night I built a full-stack web application in under ten hours. I’m not a software engineer and have near zero development experience, yet I shipped a tool that collects meeting inputs through a simple form, pulls details from internal directory and calendar APIs, formats a brief, and emails it to the intended recipients. In a large company these types of tasks are usually a time sink for busy mid-level employees. I got the job done in a single extended evening using Cline inside VS Code for orchestration, Harmony for the app framework, and JDK 17 for the runtime. I also used MCP, the Model Context Protocol that lets an AI agent securely connect to tools, files, and services without hard-coding every integration.

The use of artificial intelligence to produce internet content raises questions about authorship, originality, and moral responsibility. AI does not act independently. Its outputs reflect the instructions and intentions embedded in the user’s prompt i.e., if garbage in, then garbage out. This establishes a clear dependency where the system is shaped by the human who operates it.

When a human supplies a prompt based on their own reasoning or imagination and uses AI to refine, edit, or structure that material, the process remains rooted in the user’s authorship. In such cases, AI functions as a tool. It plays a supporting role similar to spelling correction or layout formatting. The core idea remains human, and the final product reflects an extension of the author’s thinking.