Phase 1: New Tours
We replaced our previous, error-prone location extraction with an AI-driven model. The AI reads itinerary descriptions and identifies and tags locations with much higher accuracy. This happens automatically for all newly imported tours, which appear in the TimTam queue as usual. If you manage your tours manually, use the Refresh Map from Itinerary button in the Operator Dashboard to access the same functionality.
We've also added the ability to flag "no-location" days like transit days at sea, and introduced Location Logging so that if the AI finds a place that isn't in our database yet, it gets logged to improve coverage over time.
Accurate locations mean better maps for travelers, more relevant search results, less manual cleanup for our teams, and an experience that meets traveler expectations.
Phase 2: Existing Tours
Phase 2 brought the same AI accuracy to our existing catalog. We built and deployed an outlier detection algorithm to identify tours with broken maps or mismatched itinerary locations, isolating 7,600 problematic tours for AI review. We also refined the AI to ignore "adventure summaries" like last-day recaps to prevent map clutter. Running the extraction across the board achieved a 90% success rate in fixing identified outliers.
Our tour inventory has never been more accurate in terms of location completeness.
Phase 3: Streamlined Operator Dashboard
Phase 3 simplifies location management going forward. We overhauled the Operator Dashboard, moving from a two-step process to a single, streamlined interface with fewer buttons. The map is now permanently visible, giving you real-time visual feedback as you make edits.
We've replaced general "Tour Locations" with required Day Locations to ensure maximum itinerary accuracy, and added new transit mode options for River Cruise and Sailing days so operators can mark days as transit without needing a specific map pin.
The result is a faster experience for operators and higher-quality data for travelers.
Phase 4: Auto-Syncing Updates
Phase 4 ensures that as itineraries evolve, maps evolve with them automatically. If an imported tour's itinerary text changes by more than 5% at the day level, the AI automatically triggers a fresh location extraction. We've also added a distance-and-angle check to catch errors before they reach travelers — flagging locations more than 200km off route, locations exceeding 1.2x the average route distance, and route angles narrower than 60°. Tours with detected issues or ambiguous titles are automatically routed to the TimTam Content Queue for manual review.
Our maps are now living data that stay accurate as operators update their tours, maintaining the highest quality standards on the marketplace.