536384
536384
Reminder to you & me : Let’s go touch some grass
aanchal khandelwal
© 2026
aanchalaameria@gmail.com
resume (PDF) →
Find me anywhere as aanchaling
built with love, brain and
AI in the slowly burning world
Our trips,
at one place.
How a simple trip tracker evolved into a shared travel operating system for two people grew from an Excel sheet. Multiple cities and plans that keep changing.
Goal
→
Create one secure place where both of us could see every confirmed ticket, tentative journey, booking source and traveller—and understand how each trip affected Rishi’s days in Thailand.
Problem
→
•
Bookings were scattered across different apps IndiGo, Thai Airways, AirAsia, Air India, Indian Railways, emails and booking platforms. Finding who booked what and where required repeated searching.
•
Some journeys were individual and others were together, while tentative visits home existed only in chats or spreadsheets.
•
Every arrival and departure affected the Thailand residency-day calculation. Planned journeys also needed to be counted without confusing them with confirmed travel.
Solution
→
•
Transformed our shared Excel sheet into a secure, responsive travel website with one timeline for personal and shared journeys.
•
Brought confirmed tickets and “Yet to be booked” plans together, supported by traveller filters, a calendar and Smart Trip Hubs.
•
Used GPT models to parse cities, airport codes and ticket information, reducing repetitive manual entry.
•
Built and refined the product through short prompts via phone—shipping small improvements to its logic, icons, copy and layout as we used it.
Impact
→
Our trips needed adult supervision.
With this many flights, trains and rides, even our itinerary needed a full-time manager and we build it.
The context
Our travel was spread across too many places.
Some tickets were booked directly with IndiGo, Thai Airways, AirAsia or Air India. Others came through Indian Railways or a booking platform. Some journeys were personal; some were together. Remembering who had booked what—and where the confirmation lived—became unnecessarily confusing.
Because we were long-distance for parts of the year and frequently travelled home, the work started much earlier than the booking. We had tentative dates to align, journeys still to book and Rishi’s days in Thailand to calculate.
The information lived across WhatsApp, email confirmations, calendars and memory. We used excel to plan stuff sometimes were always confused and every “when are you coming?” started another round of searching.
How might we bring confirmed bookings, unfinished plans and residency-day calculations into one shared, dependable place?
The Problem
Finding a ticket was only the visible problem.
Underneath it were four connected questions: where was it booked, who was travelling, what was still only a plan and how did every journey affect the number of days Rishi spent in Thailand?
01
Bookings had no single home
Airline apps, railway accounts, emails and chat screenshots all held different parts of the answer.
02
Ownership was easy to lose
A ticket could belong to Rishi, Aanchal or both—and either person might have booked it.
03
Planning began before booking
Long-distance coordination depended on tentative journeys that did not yet have a PNR or final date.
04
Trip changed the BKK days
Arrival, departure and planned days had to be calculated consistently, not repeatedly by hand.
Strategy
Make it useful first. Refine it through use.
People already manage flights, hotels, visas & itineraries. Connectivity is often postponed until three days, or even one day, before travel.
01
Show what matters next, then the archive.
02
Keep personal travel behind a secure login.
03
Keep ownership visible at every level.
04
Use GPT to parse cities and booking details.
How it evolved
From a spreadsheet to a travel system, one question at a time.
We built almost entirely through the chat interface on our phones. We gave it small requests, used the result, then returned with the next issue—an icon that felt wrong, a label that was unclear or a planning state that was missing. Early on, usefulness mattered more than a perfect interface. Visual consistency, responsiveness and accessibility were strengthened through later refinement passes.
Version 01 · Visibility
Giving every booked journey one home
The Excel sheet proved that a shared source of truth reduced searching. The first secure site kept that structure, but made the next departure, traveller and ticket details immediately visible.
—
One protected shared timeline
—
Rishi, Aanchal or both
—
Booking source and ticket in context
Version 02 · Planning
Give unfinished plans a place
Real travel exists before the booking confirmation. Dashed “Yet to be booked” states made intention visible without pretending that details were final.
—
Planned and booked coexist
—
Flexible-date language
—
Upload ticket when ready
Version 03 · Orientation
See the month—and what each trip changes
The calendar surfaced overlaps, weekends and gaps. A dedicated Thailand-days view then used confirmed and planned journeys to make residency planning part of the same travel system.
—
Weekend and today emphasis
—
Confirmed and planned-day counts
—
Consistent arrival/departure rules
Version 04 · Intelligence
Let GPT do the repetitive interpretation
Ticket inputs did not always name places consistently. GPT models helped parse city names, airport codes and booking details, while deterministic product rules grouped related legs into Smart Trip Hubs.
—
City and airport-code parsing
—
Related tickets grouped automatically
—
Suggestions stay attached to the journey
Handling complexity
The interface stayed simple because the model became clearer.
The breakthrough was not another screen. It was defining a small set of rules that could classify every journey consistently.
Intent
Planned / booked
A journey can exist before a ticket does. Confirmation changes its state, not it identity.
Ownership
Rishi / Aanchal / both
Ownership powers personal filters while preserving one shared source of truth.
Time
Past / today / upcoming
The same record changes prominence as time moves forward; it does not disappear.
Outcome
A personal tool that reduced coordination to a glance.
Shared clarity
Both people can see what is
confirmed, what is pending and
who is travelling.
Less re- checking
Dates, times, tickets and trip
context no longer need to be
reconstructed from chats.
A system that grows
New edge cases fit into a small
set of rules instead of creating a
new interface every time.
Reflection
The product became the process.
We did not wait for a complete specification or a perfect interface. We built through chat on our phones, used every small version in real life and refined what created friction. That made each exception an unbooked leg, a timezone ambiguity, a day-count rule an opportunity to make the system clearer, not the screen busier.
Explore more work
Next project ↗