Natural Language Tasks
Query patterns recognized by the agentic engine's plan builder
How Tasks Work
The PlanBuilder uses pattern matching to parse natural language queries. When you say "analyze my best session", it matches the ["analyze", "best"] pattern and builds a multi-step execution plan using the appropriate tools.
Session Analysis
Finds session with most swings, loads summary, detects swings, and generates visualization
Tools: find_best_session → get_session_summary → detect_swings → visualize_sessionRetrieves recent sessions and generates comparison metrics
Tools: get_recent_sessions → compare_sessionsGets synchronized Apple Watch + Zepp data for the specified date
Tools: get_linked_session_data → visualize_linked_comparisonAnalyzes the most recent session with full metrics
Tools: get_recent_sessions → analyze_apple_watch_sessionVisualization Requests
Generates density heatmap of racquet impact positions
Tools: visualize_zepp_impact_heatmapOpens interactive Zepp impact dashboard in browser
Tools: visualize_zepp_impact_dashboardGenerates timeseries visualization of session sensor data
Tools: visualize_session (viz_type=timeseries)Creates 3D visualization comparing wrist and racquet paths
Tools: visualize_trajectory (swing_index=5)Match Statistics
Returns total matches, wins, losses, and win percentage for the year
Tools: get_match_count (year=2024)Calculates overall win percentage from match history
Tools: get_match_countReturns opponent, score, and outcome of most recent match
Tools: get_latest_match_resultCounts distinct tournaments with match breakdown
Tools: get_tournament_countHeart Rate Analysis
Analyzes HR statistics by match outcome
Tools: analyze_hr_by_outcome (outcome="all")Returns max HR for winning matches
Tools: analyze_hr_by_outcome (outcome="wins")Compares average HR between wins and losses
Tools: analyze_hr_by_outcomeSensor Inventory
Lists all sensor sources with session counts
Tools: get_sensor_inventoryReturns practice session count and swing statistics
Tools: get_zepp_session_countDisplays all available data sources with record counts
Tools: show_data_sourcesData Export
Exports session data to specified format
Tools: export_data (format="csv")Pulls latest sessions from Mac server
Tools: sync_apple_watchRegenerates BabPopExt.db from app logs
Tools: refresh_babolat_data