Worktrip Autopilot
Restoring work trip efficiency through Agentic AI
A natural-language, agentic AI travel system that transforms fragmented corporate trip planning into a simplified workflow, from single sentenced intent to booking.
Role
Product Designer (UX/UI, AI Logic)
Responsibilities
User Research & Analysis, Design & Prototyping & Motion, User Interview & Testing, Product Management
Client
TravelTech Innovations
Tools
Figma, Flowise, Supabase, LLM (Grok/Gemini)
Duration
Aug 2025 - Dec 2025
PROJECT BRIEF
Today corporate travel is a "manual chaos" of disconnected tools. Travelers jump between 5+ tabs — Calendar, Slack, Policy Docs, Booking Sites — to coordinate a single trip. This forces employees to manually coordinate dates, budgets, and policies, turning a simple request into a high-cognitive-load task.
Our goal was to design an autonomous system that doesn’t just surface information, but executes coordinations—while keeping humans firmly in control.*
*In an ambiguous brief, I began by defining the core constraints of the problem, highlighted above in bold.
RESEARCH DISCOVERY
I first started by defining the "Who and Why" of corporate travel.*
Through research and ideation, we identified three critical pain points:
Filter Fatigue: Users spend 15+ mins clicking filters for every trip.
Coordination Gap: Tools are built for individuals, not teams of 3+.
Fragmentation: Lack of integration between booking and corporate policy.
*This research focused on identifying high-impact opportunities within the B2B corporate travel domain.
Interview
Heavy Manual Work
Revealed that business travelers manually juggle calendars, Slack, policy documents, and booking sites just to coordinate a single trip.
Competitive Analysis
Lack of Coordination
Showed that existing corporate travel tools optimize for individual bookings, leaving group coordination to external tools like Slack and spreadsheets.
System Mapping
Exposed a fragmented travel workflow where booking, policy, approvals, and communication are disconnected, increasing cognitive load and error risk.
Painpoints
Challenges that Corporate & Business Travelers face
Synthesized research into three high-impact challenges
REFRAMED PROBLEM STATEMENT
How might we enable business travelers to make policy-compliant work trip instantly, closing the gap between "intent" and "confirmed booking" through an autonomous agent?
SOLUTION 01
Conversational Entryway: Natural Intent Parsing
Capturing complex work trip guardrails through a single natural language prompt.
Users begin by typing a single sentence, “Book me a trip from Pittsburgh to Seattle, January 11–13, for 3 teammates.”
There are no complex option filters, forms, or drop-downs—just pure intent.
How it Works
An LLM-powered intent bar parses a human sentence to identify destinations, dates, and passengers instantly.
Strong Point
✅ Unlike static forms, the Pill Rail provides immediate visual confirmation of the agent's understanding.
Design Purpose
✅ This eliminates the "50+ click filters" by allowing users to verify captured data in real-time, building trust before the search even begins.
SOLUTION 02
Live Agent Planning: Real-Time Visible Reasoning
Turning the AI from a black box into a visible, collaborative process
SOLUTION 02-1
Autopilot agent begins planning in real time, showing progress and decision checkpoints.
Instead of instantly returning results, the system makes its reasoning visible.
How it Works
A Live Preview panel updates the planning phase in real time. Rather than feeling automated away, users stay oriented and informed by having a conversation with Autopilot.
Strong Point
✅ Unlike traditional booking bots that jump straight to outcomes, human-readable planning states ensure the user understands how the system arrived there.
Design Purpose
✅ By externalizing reasoning at the right level of detail, the Live Preview reframes AI from a opaque automation into a collaborative planning partner.
SOLUTION 02-2
Once the agent generates options, users can see what the agent is doing step by step, before results appear.
How it Works
The interface shifts from conversational updates to a system-wide planning view. Users can see a real-time checklist progress across key planning tasks.
Strong Point
✅ Instead of a loading spinner, users confirm visually with concrete planning milestones being completed.
Design Purpose
✅ By externalizing execution states, the system reduces anxiety and builds confidence, especially during moments when users typically wonder, “Is this still working?”
SOLUTION 03
Itinerary Comparison: Decision Support, Not Search
Turning overwhelming travel options into clear, strategic choices.
Instead of presenting dozens of flights and hotels, Autopilot curates three strategy-level itineraries, each optimized for a different priority—cost, balance, or time. Users don’t compare line items, they choose intent.
How it Works
Once planning is complete, the system presents three in-policy itinerary strategies.
Each option communicates tradeoffs—price, arrival time, hotel quality—without requiring manual comparison.
Strong Point
✅ Strategy-first framing replaces filter-heavy search results with clear, outcome-oriented choices.
Design Purpose
✅ By narrowing options into clear archetypes, the interface supports confident decision.
SOLUTION 04
Assured Execution: Confident Handoff to the Agent
Turning approval into a complete shareable outcome, without losing control.
Once users decide, the agent takes responsibility for execution. Booking, policy validation, confirmations, and team visibility are handled automatically, while the user remains confident everything aligns with their original intent.
How it Works
After selecting a preferred option, the user authorizes the agent to proceed.
Autopilot books flights, hotels, and transportation within policy, then presents a structured confirmation view that clearly communicates what was booked, why, and for whom.
Strong Point
✅ Instead of fragmented confirmation emails and hidden system actions, users receive a single, authoritative confirmation view that clearly explains what was booked, making the agent’s execution trustworthy.
Design Purpose
✅ By presenting execution results in a structured and shareable format, it turns delegation into confidence, allowing users stay aligned with policy and intent, without follow-up work or uncertainty.
However…
When Planning Ends, Reality Begins
Once a trip is confirmed, most systems enter a dead state.
LIMITATION
Travel itself is unpredictable. If a flight is delayed or canceled mid-trip, travelers are forced back into manual survival mode—calling support, refreshing booking sites, and trying to stay within policy under pressure.
Current travel platforms optimize for planning, not resilience.
12 In-Depth Interviews
Feel Abandoned After Booking
Participants described disruptions as moments of cognitive overload, where they were forced to re-plan manually. Once a trip is confirmed, support disappears.
+50 Survey
Confidence Drops After Booking
Only 31% felt supported during delays or cancellations, 64% reported switching to manual workarounds (calls, emails, screenshots) mid-trip
It's Time to Look Ahead
So how might WorkTrip Autopilot evolve beyond static planning?
I reimagined Autopilot as a Proactive Travel Guardian—a system that remains active, transparent, and trustworthy throughout the journey, especially during disruptions.
FUTURE SOLUTION 01
Proactive Disruption Detection
Instead of last-minute calls and emails, Autopilot speaks first.
By continuous monitoring on global flight data, it surfaces a signal directly, when a disruption is detected.
✅ The system surfaces a bottom-up alert card directly with clear signal “Agent intervention detected.”
FUTURE SOLUTION 02
Explorable Agent Reasoning
Instead of silent automation, Autopilot makes its reasoning visible.
When a disruption occurs, users can inspect why the agent acted—before approving any changes.
✅ The system exposes a human-readable activity log through “Agent Activity Log.”
FUTURE SOLUTION 03
Curated Recovery Decisions
When plans break, users don’t need more data—they need clarity.
Autopilot replaces manual comparison with strategic recovery choices.
✅ The system presents 2–3 policy-compliant recovery strategies instead of raw flight lists.
FUTURE SOLUTION 04
Clear Resolution State
After recovery, travelers shouldn’t wonder what’s still valid.
Autopilot closes the loop with a definitive, readable resolution state.
✅ The system confirms the new state of the trip using high-contrast semantic badges,
"Confirmed (new changes applied)" & "Unchanged (preserved bookings)"
IMPACT
To evaluate the effectiveness of WorkTrip Autopilot, we conducted pilot demos and comparative walkthroughs against existing corporate travel platforms.
Across testing, participants consistently reported a shift from manual coordination to confident delegation. Instead of jumping between calendars, policy documents, and booking sites, users were able to understand, approve, and trust the system’s decisions in one continuous flow.
“I don’t feel like I have to double-check everything or jump back and forth between platforms just to book one trip. I can clearly see what was booked and why, and that makes me feel secure.”
— Pilot participant
92%
Reduction in Time-to-Book
Group travel planning dropped from ~12 minutes to under 1.5minute by replacing manual filtering with intent-based planning.
100%
Policy Compliance Maintained
All itineraries surfaced were pre-vetted against corporate travel rules, eliminating out-of-policy “shadow spend” at the decision stage.
18.5%
Increase in User Confidence
Participants reported feeling more in control due to transparent planning states, readable summaries, and clear confirmation views.
KEY TAKEAWAYS
Leading this project as a UX Designer, challenged me to work deeply within ambiguity, not just designing interfaces, but shaping how humans and AI collaborate in high-stakes, real-world contexts. WorkTrip Autopilot reinforced my belief that strong AI-driven products emerge at the intersection of autonomy and control, where systems act decisively while keeping humans confidently in the loop.
Extended Work
Beyond the core product design, I contributed to the broader system thinking, technical integration, and storytelling across multiple artifacts.
Design & Research Artifacts
Technical Collaboration
Flowise — LLM orchestration and agent logic prototyping
Supabase — Data modeling and state persistence
OpenRouter — Multi-model experimentation (Grok, Gemini)
FastAPI + Google Flights API — Live flight data exploration and constraints testing
