Skip to main content
All blogs

An AI trip planner that builds day‑by‑day itineraries from real places

A travel agent’s planning tool: answer a few questions and get a streamed, editable itinerary grounded in real place search, saved and shareable.

An AI trip planner that builds day‑by‑day itineraries from real places: cover
Client
An independent travel agency
Year
2026
Status
Built
Timeline
First version in about two days

The problem

Planning an itinerary by hand is slow. The agency wanted a planner that turns a traveller’s preferences into a plan they can refine, without inventing places that do not exist.

What we built

  • An intake wizard for destination, number of days, interests, budget and pace, with AI-suggested destinations and filters
  • An agentic planner that calls a place-search tool, up to six steps per plan, so activities come from real search results
  • Itineraries streamed into the page as designed components (trip header, day headers, activity cards, notes) rather than a wall of text
  • Chat to refine the plan, saved trips, and a read-only share page with a preview image
  • Sign-in and a waitlist for early access

Stack

  • Next.js
  • Vercel AI SDK
  • OpenRouter
  • Postgres
  • Clerk
  • Vercel

Where it landed

  • Working end-to-end product, from intake to shareable trip page

Want something like this?

Tell us the idea in a few lines. We will say what week one looks like.