Salience-Triggered Output

Problem

An agent that emits on every cycle quickly becomes noise — users stop reading the channel, mute it, or close the application. An agent that emits only when explicitly asked goes silent during the moments when the user would have most wanted to hear from it, such as when a metric breaks pattern or a long-running task finishes. Without a way to score how interesting each internal event is, the team is stuck choosing between spamming and ghosting, with no middle ground that matches output rate to actual signal rate.

Solution

Score every internal event for salience (novelty + goal-relevance + recency + prediction-error - fatigue). When the score for a candidate output crosses a threshold, emit. Otherwise log and move on. Rate-limit emissions per time window.

When to use

• The agent runs on a tick or always-on loop and emits too often or too seldom.
• An internal salience signal can be defined from novelty, goal-relevance, and recency.
• Users tolerate occasional silence in exchange for less noise.