Agentic AI Product

Balancing AI Agency and User Control in Booking Worktrips

  • Shipped
  • 0 → 1
  • AI Product Design
Team
1 Product Designer (Me)
1 Software Engineer
Timeline
3 Weeks
Tools
Claude Code
Figma, Figma Make
Supabase
SerpApi
Skills
AI Prototyping
Interaction Design
Usability Testing
Systems & API Integration
Four feature panels: planning a trip in one sentence, choosing from agent-curated itineraries, seeing the trade-offs in the agent notes, and checking policy compliance.

Overview

How much should an AI agent decide on its own?

Worktrip Autopilot is an AI agent that plans, books, and manages business travel inside company policy. Describe a trip in plain language and it searches real flights and hotels, then returns three itineraries to compare. I designed and shipped v1 with a software engineer, then rebuilt the working product as v2 solo with Claude as my technical partner.

As the sole designer, I…

  • Framed the agency vs control tradeoff and designed for it across the flow
  • Collaborated with a developer, then with Claude, to ship and iterate the MVP
  • Ran user testing across four versions and translated feedback into design decisions
  • Owned visual craft and interaction design

What Improved

Impact

Reduced task completion time
-65%
AI credibility score
+28%
Confidence rating
+40%

Problem

AI agent can plan fast, but users felt low accountability

After user testing the initial MVP, three pain points surfaced. Although the AI agent could plan an itinerary in seconds, users hesitated to click Confirm & Book. They couldn’t see how decisions were made on their behalf.

  1. Users couldn’t see why the agent recommended what it did

    How much do you trust the options?

    2.75 / 5

  2. Couldn’t verify the agent’s reasoning before booking

    How confident are you clicking “Confirm & Book”?

    3 / 5

  3. Users felt limited control over the customization

    “I hope the itineraries are more micro adjustable…”

    Interviewer #4
How might we automate itinerary generation while keeping users in control of what matters?

Design Approach

Splitting the flow into what the agent owns and what the user decides

I mapped the flow decision by decision along the user journey to examine the balance between AI and user autonomy. User feedback pointed to one clear gap. The itinerary selection phase needed more user control.

Journey diagram on one timeline. Above the line, the AI agent suggests trip itineraries, then books the trip and provides an overview. Below it, the user shares trip intent and preferences, chooses an itinerary direction, then reviews, edits and confirms — the last two grouped as the phase that needed more user control.

Iteration

4 rounds of rapid prototyping

Using AI tools, I was able to iterate 4 versions of prototype within 2 weeks, focusing on the flow and usability.

The four prototype versions side by side: a five-step manual entry wizard; a three-step agent-driven flow; a version combining itinerary selection and editing; and the final choose, refine, confirm flow.

Design Decision

Redefining the itinerary selection step

After V2, three problems surfaced at once: users couldn’t compare options cleanly, they hesitated at Confirm, and they couldn’t tell how policy was applied. Instead of patching each symptom, I reframed what the itinerary step was for.

  1. Decision 1: Surfacing editing step

    I restructured the user flow to choose high level itinerary type first, then surfaced editing. Making editing its own step gave users the review moment they’d been unconsciously seeking before proceeding.

    BeforeItinerary selection & edit → Trip overview

    • Negative:Editing capability was not discoverable

    AfterChoose itinerary type → Edit → Trip overview

    • Positive:Naturally prompted to review their itinerary once more
    • Positive:Smoother flow leading into booking

  2. Decision 2: Simplifying information in itinerary cards

    Now that the user gets an editing step separately, the itinerary option card no longer needed to carry trip details like assigned seat or baggage policies. I reduced the cards to only what users need to choose a direction.

    BeforeOne detailed option

    A single long itinerary card carrying flight times, seat assignment, baggage allowance, hotel details and per-category cost.
    • Negative:Creates unintended visual hierarchy
    • Negative:Includes trivial trip details

    AfterThree simplified options

    Three equally weighted itinerary cards — Balanced, Time Saver, Cost Saver — each summarised to its flights, hotel, agent notes and total, with the same Continue button.
    • Positive:All options look equal
    • Positive:Easy to compare options

  3. Decision 3: Redesigning spend visibility for policy compliance

    The initial design showed a single budget bar per trip. It looked tidy but hid how policy actually works. Some corporate policies enforce spend by category, not by trip total. I redesigned the compliance view around category level status so the agent’s reasoning became legible.

    BeforeBudget centered itinerary view

    The earlier trip view in three policy states — action needed, in policy, review required — each showing the same one budget bar reading 94% used of the trip total.

    AfterPolicy driven compliance view

    The revised compliance view in the same three states, each breaking spend into flights, hotels, ground transport and food with its own pass, over or review status.

Design Details

Establishing trust throughout the interface

At the moments when users needed more feedback to trust the system and itinerary suggested by the agent, I designed specific UI solutions throughout the booking flow.

  • The parsed trip details shown back to the user before the agent searches — origin, destination, dates and traveller count, above a Generate options button.

    Intent confirmation before agent runs

    Users know the agent understood them before it commits to searching

  • Copy beneath the confirm button explaining what happens on booking and how to undo it.

    Reassurance copy

    Users know what happens after they click, and how to undo it

  • A hotel card with an Agent Notes panel under it, giving two reasons the option was chosen and one trade-off it carries.

    Agent notes

    Users see why each option was picked, including pros and cons

Final Design

Final flow

Validation

Balanced agency between user and AI agent relieved the trust gap

The revised design was tested with 8 business travelers across two moderated sessions.

Reduced task completion time
-65%
AI credibility score
+28%
Confidence rating
+40%

Reflection

Learnings

  1. AI agent autonomy vs. user trust

    In high stakes contexts, too much AI autonomy destroys trust. The key was reducing user effort without taking away their final decision.

  2. Balancing business constraints and user value

    I learned to balance corporate cost saving goals with employee comfort. The challenge was turning competing priorities into a transparent, fair UI.

  3. Learning through iterative vibe coding

    Iterative vibe coding sharpened my prompting intuition. It also gave me the front end knowledge to collaborate seamlessly with engineers.