Why does legacy agents fail?

The most common reason legacy agents fails: Performing the audit intellectually but refusing to act on the results. You identify five legacy agents, nod at the list, and change nothing — because each one feels too small to matter, or because you convince yourself that someday you'll need it. The accumulation is the problem. Five agents that each waste ten minutes a week cost you over forty hours a year. The failure mode is treating the audit as the endpoint rather than the input to a retirement decision.

The fix: Open your phone, your browser bookmarks, your note-taking system, and your calendar. For each, list every recurring process, saved workflow, or habitual routine that you engage with at least weekly. Next to each one, write its original purpose and whether it still serves that purpose today. Mark anything where the honest answer is 'I don't know why I still do this' or 'it used to help but doesn't anymore.' You have just completed a legacy agent audit. Count them. Most people find between three and seven.

The underlying principle is straightforward: Some agents outlive their usefulness but persist because removing them feels risky or costly. Legacy agents consume resources, create confusion, and block the deployment of better alternatives. Identifying them is the first step toward a clean epistemic portfolio.