Frequently asked questions about thinking, epistemology, and cognitive tools. 194 answers
Identify one recurring error in your work or life — a type of mistake you make repeatedly despite knowing better. Examples: forgetting to attach files before sending emails, miscalculating time estimates, overlooking a step in a multi-step process. Now design or install one automated detection.
Identify one error or failure from the past two weeks — a missed deadline, a conversation that went poorly, a habit you dropped, a decision that produced a worse outcome than expected. Spend fifteen minutes writing answers to three questions: (1) What specifically went wrong — not the emotion, but.
Identify three cognitive agents you currently run — habitual routines, decision rules, or structured practices that operate somewhat independently in your life. Write each one down with its trigger condition ('when X happens, I do Y') and its intended output. Now look for overlap: are there.
Identify a project, team, or recurring collaboration in your life where more than three people are involved. Map every coordination mechanism currently in use: meetings, status updates, shared documents, chat channels, email threads, approval workflows. For each one, estimate the total.
List your five most important cognitive agents — habits, routines, systems, or recurring commitments. For each one, write down (a) how often you currently check on it, (b) how fast it can go wrong if unattended, and (c) the cost of discovering a problem late. Now assign each agent a monitoring.
Pick one cognitive agent — a habit, routine, or decision protocol — that you have been running for at least 30 days. Write down its original specification: what triggers it, what steps it includes, what output it produces, and how long it takes. Then, honestly describe what you actually did the.
Pick one system you're currently optimizing — a workflow, a habit, a communication pattern. Create a simple log with four columns: Date, Change Made, Rationale, and Observed Result. For the next seven days, log every deliberate change. At the end of the week, review the log and answer: Which.
Pick one recurring decision you make on autopilot — what to eat for lunch, whether to check your phone when it buzzes, how to respond when a meeting runs over. Decompose it into its three components: (1) What triggers it? Name the specific situational cue. (2) What condition validates it? What.
Audit the last ten decisions you spent significant time on. For each one, classify it: Was the decision reversible (you could undo it within days or weeks at low cost), partially reversible (you could undo it but with meaningful cost or friction), or irreversible (once done, the path back is.
Pick one task you completed in the last 48 hours — a meeting you ran, a document you shipped, a conversation you had, a workout you finished. Set a timer for 15 minutes and answer these four questions in writing: (1) What did I intend to happen? Be specific — write down the concrete outcome you.
Pick one recurring correction you perform regularly — proofreading a document, double-checking a calculation, reviewing a process for mistakes. Time yourself doing it today. Write down three numbers: (1) how many minutes the correction took, (2) how many actual errors you found, and (3) what the.
Identify one recurring error in your life — missed deadlines, energy crashes, forgotten commitments, repeated arguments, or any pattern that keeps showing up despite your awareness of it. Write down: (1) what the error looks like when it manifests, (2) what early signal appears before the full.
Pick one agent (a habit, a routine, or a delegation) that you monitor. Write down three numbers: (1) the metric you track (e.g., completion rate, accuracy, time-to-fire), (2) the value you consider 'normal,' and (3) the value that would make you stop and investigate. Now ask: how did I arrive at.
Pick one agent (habit, routine, automated behavior) that you consider important but that fails more than 20% of the time. Map every instance in the last 30 days where it fired and where it didn't. For the failures, identify the specific condition that broke it — fatigue, travel, interruption,.
Select one agent — a habit, routine, workflow, or recurring process — that currently feels bloated or unreliable. List every action this agent currently includes. For each action, classify it as core (directly serves the agent's primary purpose), supporting (indirectly useful but not essential),.
Choose one agent you actively use — a decision-making heuristic, a weekly review process, a communication protocol, a problem-solving routine. Write down its current form as v_current (assign whatever version number feels right based on how many times you think it has changed). Then reconstruct.
Pick one agent or automated system you currently maintain. Open its documentation — README, wiki page, inline comments, whatever exists. Read every factual claim: data sources, triggers, dependencies, output destinations, failure modes. For each claim, mark it as current, outdated, or unknown..
Identify one recurring decision you make at least three times per week where you already know the right answer before you deliberate. Write it as an explicit agent using this format: TRIGGER (what situation activates it), CONDITION (what must be true), ACTION (what you do). Example: TRIGGER —.
For the next two hours, set a timer for every 30 minutes. When it goes off, pause and write down exactly what you were doing and whether you consciously chose to do it. Most people discover that at least half their actions in a two-hour window were automatic — habitual sequences they initiated.
Identify one recurring behavior you'd like to change. Write down its trigger, condition, and action — that's your default agent. Now design a replacement agent that uses the same trigger and condition but specifies a different action. Run the replacement for one week. Track whether the new action.
Audit your last workday. List every recurring decision you made — what to eat, what to wear, which task to start with, how to respond to routine messages, when to take breaks. Count them. Now select the three most frequent and design an agent for each using the trigger-condition-action structure.
Select one agent you currently run — a rule, habit, or protocol you follow in recurring situations. Write it down exactly as it exists in your mind right now. Then apply the specificity test: (1) Can you identify the exact trigger — the observable event that should activate this agent? (2) Can you.
List five agents currently operating in your life. For each one, label it internal (runs in your head) or external (embedded in a tool, environment, or system). Then ask: which internal agents are unreliable enough that they should be externalized? Which external agents have you internalized so.
For the next 48 hours, set a recurring hourly timer. Each time it fires, write down exactly what you were doing and whether that action was deliberate (you consciously chose it) or automatic (it happened without a decision). After 48 hours, sort your entries into two columns: Designed Agents.