Frequently asked questions about thinking, epistemology, and cognitive tools. 1647 answers
Your set of agents is an ecosystem — it needs balance and periodic assessment.
List every active cognitive agent you currently operate — every recurring commitment, routine, rule, habit, or automated behavior that runs with some regularity. For each one, rate three dimensions on a 1-to-5 scale: vigor (is it producing meaningful output?), organization (does it connect cleanly.
Assessing agents individually rather than as an interacting system. This is the most common failure. You check whether your exercise habit is 'working' and whether your deep work routine is 'working' and conclude that both are fine — while ignoring that they are fighting over the same morning.
Your set of agents is an ecosystem — it needs balance and periodic assessment.
Every new agent interacts with all existing agents — add new agents deliberately.
Every new agent interacts with all existing agents — add new agents deliberately.
Every new agent interacts with all existing agents — add new agents deliberately.
Every new agent interacts with all existing agents — add new agents deliberately.
Every new agent interacts with all existing agents — add new agents deliberately.
Every new agent interacts with all existing agents — add new agents deliberately.
Identify one agent — a tool, habit, practice, or automated process — that you have been considering adding to your current system. Before adding it, write down: (1) every existing agent it will interact with, (2) the specific interaction channel for each (shared time, shared attention, shared.
Adding agents based on individual merit without accounting for interaction effects. Each new agent looks reasonable in isolation: a productivity app, a new meeting cadence, an additional AI tool, a side project. But you are not evaluating the agent in isolation. You are inserting it into a living.
Every new agent interacts with all existing agents — add new agents deliberately.
When retiring an agent update everything that depended on it.
When retiring an agent update everything that depended on it.
When retiring an agent update everything that depended on it.
When retiring an agent update everything that depended on it.
When retiring an agent update everything that depended on it.
Identify one cognitive agent — a habit, routine, process, or tool — that you have stopped using in the past year, or that you are considering retiring. Map its dependencies: list every other process, habit, or system that consumed its output, relied on its side effects, or assumed its existence..
Removing an agent by simply stopping it without tracing what depended on it. This is the most common failure mode in personal systems, and it mirrors the most expensive failure mode in software engineering: deleting a service without checking its consumers. The agent you retired might have been.
When retiring an agent update everything that depended on it.
Periodically assess how well your agents work together as a system.
Periodically assess how well your agents work together as a system.
Periodically assess how well your agents work together as a system.