Internal-state triggers are high-risk — replace with external events or invest in interoceptive calibration before trusting them

Why This Is a Rule

Internal-state triggers — "when I feel anxious," "when I notice I'm procrastinating," "when my energy drops" — require interoceptive accuracy: the ability to correctly detect and interpret body signals and mental states. Research on interoception (Garfinkel et al., 2015) shows enormous individual variation in this ability. Some people reliably detect elevated heart rate; others can't distinguish it from normal. Some accurately sense fatigue onset; others don't notice until they're non-functional.

If your interoceptive accuracy for a particular state is low, a trigger based on detecting that state will fire inconsistently, late, or not at all. This makes internal-state triggers inherently riskier than external observable ones (Apply the camera test to triggers — if a camera can't detect the exact firing moment, the trigger is too vague). They can work — an experienced meditator may have highly calibrated interoception — but they require either replacement with a more reliable external trigger or deliberate calibration training.

Calibration training means systematically learning to detect the specific internal state: practice noticing body signals during known instances of the state, check accuracy against external measures (heart rate monitor, mood tracking), and build the interoceptive pathway through repeated deliberate attention. This is investment — it takes weeks of practice before the internal trigger becomes reliable enough to trust operationally.

When This Fires

• When designing triggers and the best candidate is an internal state (see Trigger stress agents on body signals (jaw clenching, shallow breathing), not cognitive assessment — stress impairs the ability to detect stress for stress)
• When an internal-state trigger isn't firing reliably — low interoceptive accuracy may be the cause
• When deciding between investing in interoceptive calibration vs. replacing with an external trigger
• During trigger audits when assessing reliability risk across your agent portfolio

Common Failure Mode

Assuming you can detect internal states because you can label them retrospectively: "I know when I'm stressed because I remember being stressed yesterday." Retrospective labeling uses different cognitive pathways than real-time detection. You need to detect the state as it's occurring, not after it's resolved. Most people have much lower real-time interoceptive accuracy than they believe.

The Protocol

(1) When a trigger depends on internal state detection, flag it as high-risk. (2) Option A — Replace: find the nearest external observable event that correlates with the internal state. "When I feel distracted" → "After the third time I switch apps in 5 minutes." "When my energy drops" → "At 2:30 PM" (a time when energy reliably drops). (3) Option B — Calibrate: invest in deliberate interoceptive training for this specific state. Practice detection during known instances. Verify accuracy against external measures. Budget 2-4 weeks of practice before trusting the trigger operationally. (4) Default to Option A unless the internal state has no reliable external proxy and you're willing to invest in calibration. (5) Even after calibration, monitor the trigger's firing rate (Define agent success as 80%+ firing rate, not subjective satisfaction — felt reliability systematically inflates actual performance) — interoceptive accuracy fluctuates with fatigue, stress, and attention.