Skip to content

Frontier Goal Selection Strategies & Autopilot

Generated artifact. Do not edit manually.

Generated by: scripts/build_compendia.py Regenerate with: python3 scripts/build_compendia.py --compendium didactic --web-and-tex Source of truth: docs/concept/didactic/source/

Language / Sprache: English (EN) · Deutsch (DE) | PDF: English PDF · Deutsches PDF

Compendium: §1 Feynman · §2 Autopilot · §3 Velocity · §4 Plan Status · §5 Goal-Book Planning · §6 Exam Prep · §7 Update Continuity · §8 Teacher View

2. Frontier Goal Selection Strategies and Autopilot

This chapter specifies how SkillPilot orders available next goals on the learner's frontier and how the optional Autopilot mode transitions between goals.

2.1. Frontier goal selection strategies

Once the backend determines the valid frontier (stateMachineOptions) from the skill graph, personal curriculum scope, and mastery state, selection strategies order those candidate goals to match different study habits.

Strategy 1: Random (Abwechslung)

  • Concept: Introduces variety by shuffling the currently reachable frontier goals.
  • Use case: Suited to learners who want interleaved practice across topics or want to avoid fatigue from staying in a single branch too long.
  • Implementation: The backend supplies the valid stateMachineOptions set; the client shuffles the list deterministically (or on refresh) to present a varied selection without violating requires prerequisites.

Strategy 2: Sequential (Schritt für Schritt)

  • Concept: Follows a structured progression along the curriculum tree.
  • Use case: Suited to learners who prefer completing one topic cluster cleanly before moving to the next branch.
  • Implementation: Candidate goals are ordered by their hierarchical tree position (tree index / stable goal order), prioritizing sibling goals within the current branch before advancing to subsequent branches.

2.2. Autopilot mode

Autopilot reduces navigation friction by automatically advancing the learner to the next eligible frontier goal when the current goal is completed.

Runtime behavior

  • Trigger: Fires when the current activeGoal transitions to the Mastered state.
  • Selection: Picks the first goal from the valid frontier after applying the configured selection strategy (Random or Sequential). When an active learning plan governs progression (see 8.2), plan handoff rules take precedence and generic Autopilot is suppressed.
  • Action: Invokes setActiveGoal(nextGoalId) automatically without requiring manual tree selection.

Configuration and persistence

  • UI: Configured in the Mein Lehrplan (Personal Curriculum) settings modal.
  • Persistence: Stored on the backend Learner entity (learningStrategy, autoPilot, strictMode, showGoalVisualizationsInChat) so preferences persist across sessions and devices.
  • API: Updated via PUT /api/ui/learners/{skillpilotId}/preferences using a partial JSON payload (learningStrategy, autoPilot, strictMode, showGoalVisualizationsInChat); omitted fields keep their persisted values.
  • Strict-mode interaction: strictMode determines whether frontier prerequisites are checked only within the active scope (optimistic) or across the complete global prerequisite closure (strict; see Context and Views).