Thesis in Design & Technology — 2025

Personal AI
Travel Companion

Multi-Agent Architecture for Hyper-Personalized Journeys
STAGE 1 Before Trip AGT-01 · Preference Profiling AGT-02 · Itinerary Creation AGT-03 · Booking & Mgmt STAGE 2 During Trip AGT-04 · Location Context AGT-05 · Schedule Optimizer AGT-06 · Language & Culture STAGE 4 Long-Term Value AGT-09 · Loyalty Optimizer AGT-10 · Wellness Agent AGT-11 · Trip Anticipation STAGE 3 Post Trip AGT-07 · Memory Curation AGT-08 · Feedback & Learning CORE Personal AI Orchestrator
Architecture Document  ·  Version 1.0  ·  2025
Table of Contents
  1. Executive Summary
  2. System Architecture Overview
  3. Agent Catalog
  4. Core Orchestrator
  5. Technical Stack
  6. Demo Scope
  7. Exhibition Experience Design
01 — Executive Summary

A Lifelong Companion
for Every Journey

The Personal AI Travel Companion is a multi-agent system designed to deliver hyper-personalized travel assistance at every stage of the journey — from initial inspiration to long-term travel memory. Unlike conventional travel apps that treat each booking as an isolated transaction, this system builds a continuous, evolving model of the traveler's preferences, behaviors, and aspirations.

At its core, an orchestrating AI coordinates eleven specialized agents across four distinct stages: pre-trip planning and booking, real-time in-trip guidance, post-trip curation and reflection, and long-term companion intelligence. Each stage feeds the next, creating a feedback loop that makes the system smarter and more attuned with every journey.

This architecture document provides a complete specification of the system's agent topology, data flows, technical dependencies, and exhibition implementation scope. It is intended to serve as both an academic reference and a technical blueprint for the working demonstration.

02 — System Architecture

The Four-Stage
Agent Ecosystem

The system is organized around a central orchestrating intelligence — the Core Personal AI — which coordinates four specialized stage clusters. Data and context flow continuously between stages, and a feedback loop from Stage 4 back to Stage 1 ensures the system evolves over time.

STAGE 1 Before Trip AGT-01   Preference Profiling AGT-02   Itinerary Creation AGT-03   Booking & Management LIVE ×2 STAGE 2 During Trip AGT-04   Location Context AGT-05   Schedule Optimizer AGT-06   Language & Culture LIVE ×1 STAGE 3 Post Trip AGT-07   Memory Curation AGT-08   Feedback & Learning STAGE 4 Long-Term Value AGT-09   Loyalty Optimization AGT-10   Wellness Monitoring AGT-11   Trip Anticipation CORE Personal AI Orchestrator plan → execute live → insights → profile → grow
03 — Agent Catalog

Eleven Specialized Agents
Across Four Stages

S1

Before Trip — Planning & Booking

Transforms raw travel intent into a confirmed, personalized itinerary with all reservations secured.

AGT-01
Preference Profiling Agent
Builds a rich, structured model of the traveler's style, budget thresholds, interests, and constraints through natural conversation and behavioral inference.
Inputs
  • User conversations & stated preferences
  • Past trip history
  • Explicit budget & date constraints
Outputs
  • Structured user profile (JSON)
  • Travel style taxonomy
  • Interest & constraint vectors
AGT-02
Itinerary Creation Agent
Generates complete day-by-day travel plans optimized for the user's profile — balancing must-sees with hidden gems, respecting energy levels and budget.
Inputs
  • User profile (AGT-01 output)
  • Destination, dates, group size
  • Budget envelope
Outputs
  • Structured itinerary (JSON + human-readable)
  • Activity cards with location, hours, cost
  • Map-ready coordinate set
AGT-03
Booking & Management Agent
Executes reservations across flights, hotels, and restaurants — then organizes all confirmation docs, tickets, and calendar entries into a single travel pack.
Inputs
  • Confirmed itinerary (AGT-02)
  • Payment preferences & loyalty accounts
Outputs
  • Confirmed bookings & PNR codes
  • Calendar events & reminders
  • Document pack (tickets, vouchers)
S2

During Trip — Real-Time Guidance

Acts as an always-on local guide — sensing context, resolving disruptions, and bridging language barriers in real time.

AGT-04
Location Context Agent
Monitors real-time position, crowd levels, and time-of-day to surface proactive, hyper-relevant suggestions — surfacing hidden gems before the traveler even asks.
Inputs
  • GPS coordinates & heading
  • Timestamp & local conditions
  • Crowd density signals
  • Active user profile
Outputs
  • Ranked nearby suggestions
  • Contextual alerts ("Skip the queue — enter via side entrance")
AGT-05
Schedule Optimization Agent
Continuously monitors for disruptions — delays, weather changes, closures — and automatically re-plans the itinerary, triggering rebooking actions where needed.
Inputs
  • Live itinerary state
  • Flight status feeds
  • Weather & event alerts
Outputs
  • Updated itinerary
  • Rebooking actions (via AGT-03)
  • Proactive user notifications
AGT-06
Language & Culture Agent
Provides real-time spoken translation and culturally nuanced etiquette guidance — from pronunciation help to awareness of local customs — eliminating communication barriers.
Inputs
  • User speech or typed text
  • Current GPS location
  • Target language context
Outputs
  • Spoken & written translations
  • Cultural etiquette tips
  • Pronunciation audio
S3

Post Trip — Memories & Insights

Transforms raw trip data into curated memories and actionable insights that feed the next journey.

AGT-07
Memory Curation Agent
Organizes photos, visited locations, and experiences into a coherent travel narrative — ready to share on social media or preserve as a personal travel journal.
Inputs
  • Trip photos & media
  • Location history & timestamps
  • Booking records (places visited)
Outputs
  • Organized photo albums
  • Narrative travel journal
  • Social media–ready posts
AGT-08
Feedback & Learning Agent
Captures explicit ratings and implicit behavioral signals to refine the user's travel profile — ensuring every future trip is better calibrated to their evolving tastes.
Inputs
  • User star ratings & comments
  • Behavioral signals (time spent, skips)
  • Post-trip survey responses
Outputs
  • Updated user preference profile
  • Insights report per destination
  • Recommendation model refinement
S4

Long-Term Value — The Evolving Companion

Grows alongside the traveler over years — optimizing loyalty, safeguarding wellness, and anticipating the next adventure.

AGT-09
Loyalty Optimization Agent
Tracks points, miles, and status across all programs — maximizing reward redemptions and steering booking decisions toward highest long-term value.
Inputs
  • Booking history
  • Loyalty program memberships
  • Upcoming trip parameters
Outputs
  • Redemption recommendations
  • Card & program upgrade suggestions
  • Optimal booking timing alerts
AGT-10
Wellness Agent
Monitors trip intensity, jet lag, and physical activity — proactively suggesting rest, recovery, or activity to maintain optimal well-being throughout the journey.
Inputs
  • Activity & step data
  • Trip schedule density
  • Health preferences & conditions
Outputs
  • Wellness alerts & rest nudges
  • Schedule lightening suggestions
  • Recovery activity recommendations
AGT-11
Future Trip Anticipation Agent
Proactively surfaces destination proposals — drawing on travel history, seasonal opportunities, trending destinations, and the traveler's evolving interests.
Inputs
  • Full travel history & feedback
  • Trending destination signals
  • Seasonal & pricing calendars
Outputs
  • Ranked destination proposals with reasoning
  • Optimal travel timing windows
  • Estimated budget previews
04 — Core Orchestrator

The Intelligence
at the Center

The Core Personal AI is not a passive router — it is the persistent intelligence that gives the system its character. It maintains a unified, evolving model of the traveler, mediates between agents, and ensures every interaction feels cohesive and intentional rather than stitched together from disconnected services.

Core Responsibilities

  • Maintains the unified traveler profile across all sessions and trips
  • Routes user requests to the appropriate specialized agent
  • Manages conversation context window across all stages
  • Resolves conflicts between competing agent recommendations
  • Synthesizes multi-agent outputs into a single coherent voice
  • Triggers proactive outreach when context warrants it

Technology Foundation

  • LLM backbone: Anthropic Claude / OpenAI GPT-4o
  • Multi-agent coordination: LangGraph / CrewAI
  • Persistent memory: PostgreSQL + Pinecone vector store
  • Real-time event bus: WebSocket + message queue
  • Prompt engineering: structured role cards per agent
  • Safety layer: content moderation + PII filtering
05 — Technical Stack

Infrastructure &
Integrations

AI / LLM Layer
GPT-4oClaude 3.5LangGraphCrewAI
Voice Interface
OpenAI WhisperElevenLabs TTSWebSpeech API
Location Services
Google Maps PlatformFoursquare PlacesHERE Maps
Travel & Booking
Amadeus Travel APIBooking.com APIOpenTable API
Data & Memory
PostgreSQLPineconeRedisS3
Frontend
React 18Tailwind CSSFramer MotionMapbox GL
Backend
Node.jsPython FastAPIWebSocketsDocker
External Intelligence
DeepL TranslateOpenWeatherFlightAware
06 — Demo Scope

Exhibition Implementation
vs. Full Vision

The exhibition demo presents a working proof-of-concept for the three highest-impact agents, demonstrating the core interaction loop — from preference intake through personalized itinerary generation — with voice interaction and live visual output. The remaining agents are represented architecturally and described in context.

✓ Implemented for Exhibition
  • AGT-01 — Preference Profiling (conversational onboarding)
  • AGT-02 — Itinerary Creation (real-time generation + map viz)
  • AGT-06 — Language & Culture Agent (live translation demo)
  • Voice interaction — speech-to-text input via Whisper
  • AI voice output — spoken responses via ElevenLabs
  • Real-time itinerary visualization on large screen
  • Interactive agent map — architecture visible as UI layer
○ Conceptual / Future Work
  • AGT-03 — Actual booking execution (payment integration)
  • AGT-04 — Live GPS recommendations
  • AGT-05 — Real disruption handling & rebooking
  • AGT-07 — Media curation & social sharing
  • AGT-08 — Multi-trip feedback learning loop
  • AGT-09 — Cross-program loyalty optimization
  • AGT-10 — Wearable wellness integration
  • AGT-11 — Long-horizon trip prediction engine
07 — Exhibition Experience

The Installation:
Travel Intelligence, Live

The exhibition presents the system as an immersive, large-format installation. A visitor approaches a floor-standing screen — the AI companion appears and initiates a natural conversation about their dream destination. Within minutes, a personalized itinerary materializes in real time, with a live map, day-by-day activities, and cultural insights. The full agent architecture is visible as a live background layer, making the system's intelligence transparent and visceral.

01

Approach & Engage

Visitor approaches the screen. The AI avatar activates and greets them with a spoken welcome. Keyboard available as fallback input.

02

Dream Destination

The AI asks: "Where have you always wanted to go?" — Preference profiling begins, extracting travel style and interests in natural dialogue.

03

Live Itinerary

A map materializes. Day-by-day activities appear in real time as the Itinerary Agent thinks — visitors watch the plan build itself.

04

Language Demo

The AI demonstrates the Language Agent — offering a phrase in the destination's language, with pronunciation and cultural context.

05

Architecture Reveal

The background agent map animates — showing which agents activated, the data flows, and how the system made its decisions.