The irreducible epistemic atoms underlying the curriculum. 4,828 atoms across 8 types and 2 molecules
Follow the automation hierarchy of eliminate-simplify-automate in strict order, because automating waste entrenches it and automating complexity makes it brittle.
Automate only tasks where the rule can be stated completely (fixed rule, known inputs, predictable outputs) and execution requires no judgment about exceptions or novel cases.
Maintain an automation registry listing each automation's function, tool, last verification date, failure indicators, and review cadence to prevent automation debt accumulation.
Start automation at the lowest-tech level that solves the problem (checklists, templates, calendar events) before considering platforms or scripts, because simplicity reduces maintenance burden.
When the same symptom triad precedes system failures across three independent incidents, document it as a named detection pattern and build an automated alert triggered by that specific combination.
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.
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.
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.
Audit your work week by categorizing each decision as 'routine' (similar decision made before, could use framework) or 'novel' (requires fresh thinking), then for the five highest-frequency routine decisions, draft simple frameworks (default answer, two-option heuristic, or pre-commitment rule) and implement all five within one week.
Deploy automated grammar checkers, linters, or mechanical validation tools before manual review to catch pattern-based errors, reserving human attention for contextual judgment that tools cannot provide.
When sustained attention must monitor for low-frequency errors over extended periods (>30 minutes), delegate detection to automated systems rather than relying on human vigilance, because attentional resources degrade predictably regardless of motivation.
Default to the delegation hierarchy sequence: first ask 'can a system handle this?', then 'can a system handle 80% with a person handling exceptions?', and only then 'does this require full human judgment?'—to prevent systematic under-investment in systems.