Rules
1,053 rules · page 10 of 22
Apply the problem-vs-polarity test — if new information…
Before attempting to resolve any persistent organizational tension, apply the problem-vs-polarity test: can new information or analysis make one side permanently win? If no, design oscillation management rather than searching for resolution.
When credentialed experts contradict each other, treat…
When two credentialed experts contradict each other on the same question, treat their disagreement as a map of genuine uncertainty in the evidence base rather than as a problem requiring you to pick a winner.
Ask 'why do these experts disagree' not 'who is right'…
When experts disagree, ask 'why do they disagree' rather than 'who is right' to identify structural sources like different methodologies, populations, or outcome measures.
Resolve contradictions at the principle level once…
Address contradictions at the strategic principle level rather than re-adjudicating them at each tactical decision point to prevent decision multiplication.
Your steel man isn't ready until advocates say 'Yes…
When steel-manning an opposing position, verify adequacy by checking whether advocates of that position would say 'Yes, that is exactly what I mean' before proceeding to critique.
Your operating principles must explain your actual…
When articulating your core operating principles, require that each principle explain your actual observed behavior patterns rather than aspirational values, because a unified theory must match behavioral data not wishes.
Audit each schema's implicit assumptions, then…
For each schema, list assumptions it makes—things it takes for granted without defining—then compare assumption lists across schemas to find shared dependency gaps where both schemas assume the same foundational concept but neither defines it.
When a cross-domain analogy breaks down, investigate…
When a cross-domain mapping breaks down or fails, investigate the mismatch systematically rather than forcing the analogy—mapping failures reveal domain-specific structural features that successful mappings cannot expose.
Apply the scramble test to schema connections…
When two schemas appear to share a concept or principle, test whether the connection is genuine by attempting to scramble the specifics—if the 'connection' would work equally well between any two randomly selected schemas, you've found semantic coincidence rather than structural isomorphism.
After an insight "clicks," test if you can now…
After experiencing what feels like an insight or integration moment, verify whether it represents genuine integration by testing whether you can now do something you could not do before—if the click produced no new capability, inference, or prediction, you experienced fluency or familiarity rather than structural integration.
If integration requires reshaping one schema to fit…
When an attempted integration between two schemas forces you to reshape one schema to fit the other rather than discovering a higher-order structure that accommodates both unchanged, you are executing Procrustean integration—abandon the attempt and either maintain the schemas separately or search for a genuinely encompassing framework.
When frameworks 'click together,' immediately write what…
After experiencing a moment when previously separate frameworks 'click together', write down specifically what you can now do, see, or infer that was unavailable before the integration—this functional test distinguishes genuine structural integration from mere exposure effects disguised as insight.
Diagnose failing behavioral agents by component — trigger…
When a designed agent fails to fire consistently after two weeks, diagnose whether the trigger is not salient enough, the condition is too restrictive, or the action requires too much effort, because each failure type requires different corrections.
Only automate decisions that are frequent, stable…
Design agents only for decisions that score high on frequency (recurring often), stability (same answer each time), and low individual stakes, because these three properties determine whether automation saves resources without introducing unacceptable risk.
Measure behavioral agent progress by displacement rate…
Track agent displacement by measuring the percentage of times your designed agent fires instead of the default, not by whether you execute perfectly every time, because replacement is gradual and competes against thousands of prior reinforcements.
Never automate decisions with genuine per-instance novelty…
Do not automate decisions where the outcome is genuinely different each instance even if the category recurs (interpersonal conflicts, creative problems, novel diagnoses), because automating decisions with genuine novelty produces rigidity disguised as efficiency.
Write all three components of default agents — even…
When reverse-engineering a default agent, write down all three components (trigger, condition, action) even if the condition is 'always' or appears absent, because making the implicit condition explicit reveals where the default fires indiscriminately.
Agent triggers must be observable or measurable — vague…
Define agent triggers as observable external events or measurable internal states rather than subjective feelings or abstract conditions, because vague triggers cannot be recognized reliably when they occur.
Review new agents weekly, established ones monthly…
Set agent review cadences at 7 days for new habits, 30 days for established behaviors, and immediately after any major context change, because review timing must match the actual rate of drift in each agent type.
Define agent success as 80%+ firing rate, not subjective…
Define agent success as a measurable outcome with a minimum acceptable firing rate threshold (typically 80% over one week for new agents) rather than subjective satisfaction, because subjective assessment systematically inflates reliability perception.
Externalize high-stakes agents to tools and environment…
Externalize critical reliability agents (medication, safety checks, high-stakes commitments) to tools or environments rather than trusting biological memory, because internal agents degrade precisely when stakes are highest—under stress and cognitive load.
Audit agents with hourly momentary sampling…
Use hourly momentary sampling over 48+ hours rather than end-of-day recall when auditing behavioral agents, because retrospective memory systematically overweights salient successes and underweights invisible failures.
Classify every behavior as designed or default…
Classify each observed behavior as designed (you can identify the installation decision) or default (no identifiable decision point) during audits, treating the classification question itself as a detection mechanism for unexamined automation.
When an agent fires below 80% after 30 days, simplify…
When an agent fires below 80% of expected opportunities over 30 days, reduce it to the simplest executable version before adding any complexity, because unreliable agents cannot be improved through sophistication.
Start every new agent at under two minutes with zero…
Design minimal viable agents to execute in under two minutes with zero preparation before attempting multi-step sequences, because automaticity requires low activation energy and activation energy must be minimized before sophistication is added.
Decouple independent sub-behaviors into separate agents…
When agent sub-behaviors can execute independently without logical dependency, separate them into distinct agents with independent triggers rather than coupling them into sequences, because coupled agents produce cascading failures.
Document every agent with five components
Document every agent in a structured five-component format: (1) Name, (2) Trigger, (3) Conditions, (4) Actions, (5) Success criteria, to enable systematic review and prevent silent degradation.
Write agent actions as procedures a stranger could follow…
Write agent action steps as specific ordered procedures rather than aspirations or principles, requiring sufficient granularity that someone unfamiliar could execute them without clarification.
Log every agent misfire with date, name, event…
Maintain a failure log where every agent misfire is recorded with date, agent name, what happened, and hypothesis about why, then review weekly to extract patterns.
Diagnose before redesigning — identify whether trigger…
When an agent fails, diagnose which component broke—trigger (never activated), condition (activated but context wasn't right), or action (executed but too vague/complex)—before attempting any redesign.
Change one agent component per iteration — multi-variable…
Fix only one component (trigger, condition, or action) per agent iteration rather than redesigning multiple components simultaneously, to maintain causal attribution of what changes produced which effects.
Name the schema before building the agent — a reliably…
Before building any agent, explicitly name the schema it operates on by writing what the agent assumes about how the world works, because unexamined schemas produce systematically wrong outputs despite reliable execution.
Debrief difficult social interactions in 5 minutes…
After any difficult social interaction, complete a 5-minute written debrief comparing what your social agent prescribed versus what you actually did, documenting the gap to update the agent based on real behavioral data.
For once-in-career decisions, suspend your agent…
When a decision situation represents a once-in-career strategic pivot rather than a routine recurrence, suspend your decision agent and return to full deliberation even if the agent would produce an answer.
Update decision agents after every activation based…
After each decision agent activation, update the agent's criteria based on whether they produced a good outcome, treating the agent as a living heuristic that improves with each use rather than a permanent law.
Set hard time-based triggers for sleep agents — fatigued…
For sleep agents, set a hard time-based trigger (like 9:30 PM) rather than a subjective state trigger (like 'when I feel tired'), because fatigued brains systematically misjudge their own tiredness.
Build nutrition agents at meal prep, not consumption…
Build nutrition agents at the meal preparation layer (Sunday evening meal prep) rather than the consumption layer (what to eat when hungry), because deciding what to eat while hungry and facing an open refrigerator is too late to override depletion.
Trigger stress agents on body signals…
For stress management agents, use physiological signals (chest tightening, jaw clenching, shallow breathing) as triggers rather than cognitive assessments ('when I feel stressed'), because stress impairs the self-assessment capacity needed to recognize stress.
Resolve inter-agent conflicts with documented priority…
When discovering that your designed agents conflict with each other, resolve the conflict through documented priority hierarchies rather than case-by-case deliberation, making the resolution rule itself part of your agent system.
Agent system review is essential maintenance, not optional…
Build feedback loops into agent systems through regular review asking whether agents fired, whether they produced intended outcomes, and whether conditions have changed, treating review as essential maintenance not optional improvement.
Apply the camera test to triggers — if a camera can't…
Design triggers using the camera test: if a video camera could not detect the exact moment the trigger fires, the trigger is too vague to fire reliably and must be replaced with an observable event.
Internal-state triggers are high-risk — replace…
When a trigger depends on detecting an internal state, classify it as high-risk and either replace it with an external observable event or invest in deliberate interoceptive calibration before trusting it operationally.
Place trigger objects at eye level in routine paths…
Place environmental trigger objects at eye level or in the direct path of existing routines rather than in convenient storage locations, maximizing visibility over proximity.
The first five consecutive executions of a new trigger…
Protect the first five consecutive executions of any new time-based trigger as non-negotiable, treating early repetitions as infrastructure investment that determines whether the trigger becomes automatic or dies silently.
Stack time + location + preceding action into compound…
Stack temporal triggers with spatial and state anchors (specific time plus specific location plus specific preceding action) to create redundant activation pathways that survive if any single trigger component fails.
Subtract unwanted affordances before adding desired ones…
Remove or relocate objects that afford unwanted behaviors before adding objects that afford desired behaviors, because elimination removes temptation entirely while addition only competes for attention.
Replace maintenance-dependent triggers with static…
When an environmental trigger requires daily resetting or maintenance to remain visible, replace it with a static persistent cue that survives without intervention, because maintenance costs compound and cause trigger decay.
Emotional trigger actions must be executable while…
When designing emotional trigger agents, ensure the action is executable within the emotional state itself rather than requiring the emotion to already be regulated.