The question I get most right now is "what should I turn into an AI agent?" Here is the 5 part test I use (works for Claude/Codex/Grokbot etc): 1. It has a repeated trigger, so the same kind of task keeps happening over and over. 2. The inputs are stable, so the information comes in a predictable shape every time. 3. The tools are clear, so there is a defined set of things it can actually go do. 4. There is a measurable finish line, so you can tell when it is done and whether it worked. 5. There is judgment in the middle, so each run is a little different and needs a real decision made in the moment. The first 4 are really just asking "can this be automated at all?" The 5th is the one that matters, because judgment in the middle is what makes it an agent instead of a simple automation. Once you see it this way, you start spotting agent work pretty much everywhere.