agent-coding-the-spiral-back-to-fumbling

⋯ 12 unchanged lines
   
  I've been using Agent Coding quite a lot these past few months. Claude Code, Cursor, Copilot — the whole lot. And I noticed something interesting that I'm not sure others feel too.
   
− The feeling of sitting with an AI agent to build a feature — it's identical to how I learned programming when I first started. About 10 years ago.
+ The feeling of sitting with an <TermNote id="agent">AI agent</TermNote> to build a feature is identical to how I learned programming when I first started. About 10 years ago.
   
  Eerily identical.
   
⋯ 35 unchanged lines
   
  Now I sit with Claude Code, and the workflow looks like this:
   
− I describe what I want. Agent writes code. Run it. Wrong. I explain more clearly. Agent fixes. Closer but not quite. I adjust the prompt, add context, clarify constraints. Agent tries again. Better this time. But there's an edge case. I point it out. Agent fixes. Works.
+ I describe what I want. Agent writes code. Run it. Wrong. I explain more clearly. Agent fixes. Closer but not quite. I adjust the <TermNote id="prompt">prompt</TermNote>, add context, clarify constraints. Agent tries again. Better this time. But there's an edge case. I point it out. Agent fixes. Works.
   
  Sound familiar?
   
⋯ 27 unchanged lines
   
  Back then I debugged semicolons. Misspelled variables. Off-by-one loops. `undefined is not a function`. I was wrestling with **syntax** and **basic logic**.
   
− Now I don't debug syntax. I debug **intent**. I'm learning how to express what I want so the agent understands correctly. How to decompose problems so the agent can handle each piece. How to set context so the agent doesn't hallucinate things I don't need. How to review output so I don't miss logic errors hidden behind fluent-looking code.
+ Now I don't debug syntax. I debug **intent**. I'm learning how to express what I want so the agent understands correctly. How to decompose problems so the agent can handle each piece. How to set context so the agent doesn't <TermNote id="hallucination">hallucinate</TermNote> things I don't need. How to review output so I don't miss logic errors hidden behind fluent-looking code.
   
  Back then I searched "how to center a div." Now I'm trying to tell AI "this layout needs to be responsive but not regular grid — more like masonry, but the first item should span 2 columns on desktop."
   
⋯ 1 unchanged line
   
  Back then I copy-pasted from Stack Overflow and tweaked it. Now I review agent-generated code and tweak it to match my intent.
   
− The core loop hasn't changed. But everything has shifted up one level of abstraction.
+ The core loop hasn't changed. But everything has shifted up one level of <TermNote id="abstraction">abstraction</TermNote>.
   
  ## A spiral, not a circle
   
⋯ 88 unchanged lines