Let's Go Christo!

Daytripper

A travel planner built in one overnight session to learn OpenAI Codex. Pick Lisbon, Tokyo, or Mexico City, set budget, time, vibe, pace, and interests, and get one thoughtful day plan with an honest cost estimate and a "why this fits" explanation. Deliberately zero LLM calls at runtime - a deterministic scoring engine, with tests that run all 1,296 possible preference combinations and check every plan is chronological, in the right city, and under budget. Next.js 16 on Cloudflare Workers via vinext.

Codex OpenAI Next.js React 19 Cloudflare Workers Evals Open Source

The fastest way to drain the joy out of a free day in a new city is to spend it researching what to do. Daytripper turns a few preferences into one confident day plan: three cities, a budget, a time window, a vibe, a pace, up to three interests, then swap stops, add budget-gated extras, save to localStorage, and share.

I built it to learn how Codex works in August 2026 - the full loop from brief to plan to build to review to test to launch. The app intentionally contains no AI at runtime: a curated pool of 36 activities and a deterministic scoring engine mean every one of the 1,296 preference combinations is testable, and all 1,296 pass. The build story, including the first prompt that produced the wrong app, is in the write-up. The repo’s LEARNING.md documents what the project teaches.

Share this post