Frequently asked questions about thinking, epistemology, and cognitive tools. 567 answers
Treating a newly deployed agent like an established one. You assume that because you designed it well and it worked the first few times, it will keep running on its own. It won't. New agents don't have the neural grooves, the environmental cues, or the social reinforcement that established agents.
Treating a working agent as a finished agent. The most common maintenance failure is not neglecting broken systems — it is neglecting functional ones. When something is working, there is no pain signal to trigger a review, no crisis to force attention. So the agent runs unexamined until it.
Two opposite errors are equally common. The first is compulsive evolution — endlessly patching an agent that should have been retired three iterations ago, because you built it and you feel attached to it. The second is compulsive replacement — scrapping agents at the first sign of difficulty and.
Treating retirement criteria as theoretical rather than operational. You read this lesson, nod, and think 'I should probably retire some agents.' But you do not write specific, measurable criteria in advance. Without pre-committed criteria, every retirement decision becomes a real-time judgment.
The most common failure is retiring the agent without retiring its responsibilities — stopping the behavior while assuming that what the behavior produced will somehow continue to happen on its own. This is the organizational equivalent of firing an employee without reassigning their tasks. The.
Retiring an agent without a succession plan and assuming nothing will break. The responsibilities don't disappear — they become invisible gaps. You notice the damage weeks later when a commitment falls through, a habit decays, or a system you relied on quietly stops producing results. The failure.
Treating past agents as embarrassments rather than evidence. You remember the system you built and abandoned, feel a twinge of shame about the wasted effort, and avoid examining it closely. This is the archaeological equivalent of bulldozing a dig site because the ruins are ugly. The information.
Treating the portfolio view as a reason to create agents for every gap you find. You see three domains with zero coverage and immediately start building new habits for all of them. Now you have twelve agents running simultaneously, your cognitive overhead doubles, and half of them fail within two.
Treating all agents as equally important and never retiring any of them. This is portfolio drift — the cognitive equivalent of letting your investment allocations wander unchecked. You'll know you're in this failure mode when you feel vaguely overwhelmed by your own systems but can't name which.
Inheriting too much. The most common failure in agent inheritance is treating the parent agent as a fixed template and copying it entirely rather than selectively extracting the components that are actually relevant. A person who has a reliable morning exercise agent tries to build a morning.
Treating templates as rigid prescriptions rather than flexible scaffolding. The person who falls into this trap creates a single 'master template' and forces every new agent to conform to it, regardless of fit. A boundary agent gets shoved into a routine template. A creative practice gets squeezed.
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.
Adding agents without retiring them, because each new agent passes the individual value test — it produces more value than it costs to run in isolation. The failure is evaluating agents individually rather than evaluating the system. An agent that produces ten minutes of value but adds fifteen.
Treating all agents as if they need equal attention regardless of stage. Mature agents get fussed over when they should be left alone. Fragile new agents get ignored because older ones feel more important. The portfolio degrades not from any single agent failing, but from attention being allocated.
The primary failure is treating agents as permanent installations rather than living processes with natural lifespans. You design an agent, it works, and you assume it will work forever. This is the cognitive equivalent of planting a garden and never weeding — the original plants may still be.