Only automate decisions that are frequent, stable, and low-stakes — all three must hold or automation introduces risk
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.
Why This Is a Rule
Decision automation — creating behavioral agents, if-then rules, or defaults that eliminate the need for deliberation — has enormous cognitive savings potential. But it's only safe when three conditions jointly hold. Frequency: the decision must recur often enough to justify the upfront design cost. Stability: the optimal answer must be the same each time (or nearly so). Low stakes: any individual instance of the decision must be recoverable if the automation gets it wrong.
Missing any one condition creates distinct problems. High-frequency + stable + high-stakes: you're automating consequential decisions with no deliberative override — a single context change can cascade automated errors through high-impact outcomes. High-frequency + low-stakes + unstable: the optimal answer varies by context, so the automation frequently produces suboptimal results, accumulating small losses. Infrequent + stable + low-stakes: the automation works but saves negligible cognitive resources because the decision barely occurs.
The sweet spot for automation: what to wear to the office (frequent, stable dress code, low-stakes individual instance), morning routine sequence (daily, same steps, individually trivial), email triage rules (constant, consistent categories, low per-email stakes). Not for automation: hiring decisions, strategic pivots, relationship conflicts — infrequent or high-stakes or context-dependent.
When This Fires
- When considering whether to create a behavioral rule, default, or automated decision
- During cognitive load audits when identifying which recurring decisions to offload
- When someone suggests "let's just make a rule for this" — check the three criteria first
- When evaluating existing automation that seems to be producing poor results
Common Failure Mode
Automating decisions that are frequent and low-stakes but unstable: "I'll always say yes to coffee meetings." The frequency and low individual stakes make this feel safe to automate, but the optimal answer varies — some meetings are valuable, some waste hours. The automation removes the deliberation that would distinguish valuable from wasteful, and the accumulated cost of indiscriminate yes-saying is high even though each individual meeting seems low-stakes.
The Protocol
(1) For any decision you're considering automating, score three dimensions: Frequency: does it recur at least weekly? Stability: would you give the same answer >90% of the time? Stakes: is any single instance easily recoverable if wrong? (2) All three must score high. If any dimension scores low, keep the decision deliberative. (3) For decisions meeting all three criteria, design the automation: specify the trigger, condition, and default action. (4) Build in a review cadence: even well-designed automation can become outdated as context changes. Quarterly check: is the decision still frequent, stable, and low-stakes? (5) When in doubt, err toward deliberation. The cost of unnecessary deliberation is time; the cost of inappropriate automation is systematically wrong decisions you don't notice.