Workflow · saas · workflow
Google optimizes trip-planning itineraries with a hybrid LLM and constraint-optimization system
LLMs handle soft qualitative preferences well but are unreliable at hard logistical constraints like opening hours, travel times, and scheduling feasibility, producing itineraries with impractical elements.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Trip query received
A user's trip-planning query is received by the system.
Tools used
Geminisearch backends
Outcome
The hybrid system produces itineraries that are practical and feasible, correcting LLM-generated plans through optimization while preserving the user's qualitative intent.
Grounding & classification
Source type: technical build writeup
13 fields verified against source quotes.
content generationpersonalizationknowledge baseproduction runtime claimedtools describedworkflow describedsoftwaretravelaccuracy improvementtechnical build writeupagentic task execution