A trip page reshaped over three rounds of critique.

Most trip planners hand you one or the other. BaconAI puts both side by side: an itinerary split into days, each with timed stops and a theme, and a map whose numbered pins follow the same sequence.

The first version was a dark hero with white text, the default look of a hundred demos. I compared a few directions and chose a warm magazine style: cream paper, charcoal text and one coral accent.

The first landing page read like a sales page. I stripped it back so the empty space did some work: one field that accepts a plain sentence, quick-pick destinations so nobody faces a blank box, and three steps underneath.

Each round started with me using it and writing down what felt wrong. Round one: the buttons were too small, the sharp corners felt hostile, and the map looked awkward squeezed at the side.

Round two: I made each stop open the map on itself. Round three: I reversed that, because you lost the overview of the day. Every stop is now plotted from the start, day filters narrow the map, and opening a stop offers three nearby alternatives you can swap straight in.

An itinerary that zigzags across a city looks fine as a list and falls apart on a map. The planner clusters each day by neighbourhood, respects opening hours and meal times, leaves travel time between stops, and keeps a comfortable pace.

Every stop shows the address, how long to allow, and whether it's free or roughly what it costs. Alternatives carry the same details, so you're comparing like with like.

I switched mapping providers for a free tier, and the language model behind the planner changed three times as free tiers ended. Knowing what a platform will actually cost, and letting that reshape the experience, belongs in the design.

Highlighting a stop used to make the map stutter, because every change redrew it. Updating the map directly made selection feel instant. An engineering fix, but I only found it because the interaction felt off.