index 010afb5..8d3a2d6 100644
@@ -15,4 +15,4 @@ a better version of Morgen (or any AI scheduling tool) that solves two problems
the scheduling problem is harder than it looks because it requires a model of the task itself, not just its time cost. a task that takes 2 hours is very different from one that takes 20 minutes active + 100 minutes waiting. the system would need to learn, over time, which of your tasks have wait-time signatures and start predicting them. the auto-planning component would decompose a high-level task like "prep for meeting with X" into component steps, estimate each, and slot them in reverse from the deadline. this is essentially a planning agent with calendar access.
-connects to [[universal-habits|universal habits]] which tackles the same underlying problem of intelligent adaptation to your actual context and state. [[ifttt-personal|personal IFTTT]] overlaps on the automation-triggers side — if a build finishes, trigger the next task. [[task-optimization-game|task optimization game]] is the gamified version of the same scheduling problem. [[cognitive-foom|cognitive foom]] is the agent-infrastructure layer that would make this kind of adaptive planning agent possible at quality. [[overnight-app-grinder|overnight app grinder]] is adjacent — it's the fully autonomous version, where the scheduler just runs tasks without human intervention during off-hours.
\ No newline at end of file
+related: [[universal-habits|universal habits]], [[ifttt-personal|personal IFTTT]], [[task-optimization-game|task optimization game]], [[overnight-app-grinder|overnight app grinder]]
\ No newline at end of file