How I Built a Complete Travel Planner App This Weekend Using ChatGPT 5.5 (No Coding Required)

Over the last few days I put ChatGPT 5.5 and Codex to the test in a serious way. I started vibe coding on Monday and finished today (Thursday April 27th). Roughly 10 hours total time invested — and at least half of that time was spent testing features thoroughly. The 1st hour was spent doing it wrong then I started over. The last hour was figuring out how to setup GitHub to load it there. This wasn’t casual weekend tinkering; it was focused, deliberate work.

The result is a fully functional, mobile-first Travel Log app that I’m actually going to use for my upcoming trip. It’s live right now at travel.jdb.net.

What I Built

A clean, self-contained travel itinerary manager with:

  • Trips grouped by name and automatically sorted by earliest event

  • Events sorted chronologically inside each trip

  • Compact one-line display (date • time • bold location • description)

  • Full add / edit / delete for events and trip names

  • Instant search across every field

  • “Not booked” items automatically highlighted in red

  • Import from pasted text or file (with review step before committing)

  • Export clean text itineraries that can be re-imported

  • One-click PDF export (print-optimized, page breaks between trips, events kept together)

  • Reload the built-in 2027 sample itinerary anytime

  • 100% localStorage — no account, no server, works offline (if installed offline).

It currently ships with two incomplete sample trips: an Alaska cruise and a 17-event Spain itinerary.

Security: Everything persists in the browser and feels native on mobile. No data lives on the cloud only on your computer if you want to try it out. That said, I have made only minimal security evaluations of this app and it’s intended for demonstration purposes only. Use it with real data at your own risk. I’m using a local copy of the app for my real trip data.

How I Built It (Vibe Coding in Practice)

I followed the exact workflow I learned in the Generative AI Bootcamp:

  1. Wrote a clear PRD (Product Requirements Document) first

  2. Used ChatGPT 5.5 and Codex to generate the initial structure

  3. Iterated with precise follow-up prompts: “Make the search instant across all fields”, “Add typed-name confirmation before deleting a trip”, “Highlight ‘not booked’ in red”, “Generate a clean PDF export with proper page breaks”

  4. Tested every single flow repeatedly — adding events, importing notes, exporting PDFs, checking mobile layout, edge cases, etc.

The 5-hour testing investment paid off. The app feels solid because I caught and fixed dozens of small issues before they ever reached the live site.

Why This Matters

  • If you’ve ever wanted a custom internal tool, client portal, lead tracker, or operational dashboard but didn’t have the budget or timeline for traditional development, this approach is now genuinely viable.

  • You can go from idea to working, usable prototype in a single focused day (or a few evenings). The remaining polish still benefits from human oversight, but the barrier has dropped dramatically.

  • I’m not claiming this replaces professional developers. I am saying the cost and speed of testing new ideas has improved by an order of magnitude. I do have programming experience and I used that to direct the AI, but at no time did I write or look at any code.

What’s Next

I’m already thinking about the next small tool I want to build the same way. The pattern is addictive once you experience it.

If you’re a business owner or operator sitting on an app idea because “we don’t have developers” or “it would take too long,” let’s talk.

I’m now helping companies build AI-generated apps and internal tools using ChatGPT 5.5, Codex, and the same vibe-coding process. We start with a clear requirements document, deliver a working prototype quickly, and iterate until it fits your actual workflow.

Reach out if you want to explore what’s possible for your business. No hard sell — just a practical conversation about whether this makes sense for what you’re trying to solve.

The 10-hour experiment is complete. Turning these capabilities into real business advantage is where the interesting work begins.

Travel Log — because good trips deserve good records, and good records shouldn’t require a complicated app.

Live demo: https://travel.jdb.net

What kind of internal tool or app would you build first if the technical hurdles were this low? THEY ARE! Send me comments here: I read every comment.

Next
Next

Ultimate Guide to AI Inference Chips as of February 2026: Top Picks and Emerging Tech