Yuga Planner

Breaks down unstructured task descriptions into discrete, schedulable subtasks using LLamaIndex's document parsing and semantic chunking. The system analyzes task dependencies, estimated durations, and priority signals from natural language input, then structures them into a hierarchical task graph that respects logical ordering constraints and resource availability.

Integrates decomposed tasks with existing calendar data using Timefold's constraint satisfaction solver to find optimal scheduling that respects availability windows, task dependencies, and resource constraints. The solver uses mixed-integer programming patterns to minimize scheduling conflicts and maximize calendar utilization while respecting hard constraints (blocked time, dependencies) and soft constraints (preferred time slots, task clustering).

Analyzes semantic relationships between decomposed subtasks to infer and enforce logical dependencies (e.g., 'design must precede implementation'). The system builds a directed acyclic graph (DAG) of task dependencies extracted from task descriptions and metadata, then uses topological sorting to ensure scheduling respects critical path constraints and prevents impossible orderings.

Scans existing calendar entries (personal, team, shared calendars) to identify scheduling conflicts and availability windows before proposing task placements. The system maintains a unified view of calendar constraints across multiple sources, flags hard conflicts (overlapping events), and identifies soft conflicts (back-to-back meetings, insufficient buffer time), then feeds these constraints to the scheduling optimizer.

Estimates task duration and effort from natural language task descriptions using LLM-based analysis combined with heuristic patterns (task complexity signals, scope indicators, historical patterns). The system analyzes description length, complexity keywords, resource requirements, and dependency count to produce probabilistic duration estimates with confidence intervals, enabling more realistic scheduling than fixed assumptions.

Converts optimized task schedule into calendar events and exports to standard formats (iCalendar, Google Calendar, Outlook) or APIs. The system creates calendar entries with task metadata (description, dependencies, priority), generates event notifications and reminders based on task type, and handles recurring or multi-day tasks by creating appropriate calendar structures.

Enables interactive refinement of generated schedules through constraint adjustment and re-optimization. Users can modify task durations, add/remove constraints (e.g., 'no meetings after 5pm'), adjust priorities, or manually override specific task placements, then trigger re-solving to find new optimal schedules respecting the updated constraints. The system tracks constraint history and enables rollback to previous schedule versions.

Analyzes task descriptions to extract and infer priority signals (explicit priority markers, deadline urgency, dependency criticality, business impact keywords) and uses these to weight scheduling decisions. The system assigns priority scores based on semantic analysis, deadline proximity, and critical path position, then feeds these weights to the optimizer to prefer high-priority tasks in scheduling conflicts.