Originally published on robatdasorvi.com
The agent you are about to build should be a for-loop with four if-statements, and the only reason it isn't one is that nobody has ever been given a budget line item for a for-loop.
I know your situation. You have a task that involves a language model somewhere in the middle. You have read that agents are the future. You have a diagram with boxes labeled planner, executor, and critic, and the boxes have arrows that loop back on themselves, and it looks like an architecture. Nobody will tell you to avoid AI agents here, because saying so sounds like saying you don't believe in electricity. So you're going to build it, it's going to work in the demo, and then it's going to spend eight months in the state that Gartner politely calls "pilot."
Let me tell you the thing I wish someone had told me before I spent a quarter learning it by hand.
Should I use an AI agent or just write the code?
