Health, home and travel decision

Wanderlog Pro

A competent developer can build a usable itinerary+map planner with sharing and basic booking import in about a week, but reproducing Wanderlog's scale, place data, polished mobile apps, and integrations would require more engineering and partnerships.

Visit website
Subscription$5.99/month
Initial build30 hours
Monthly upkeep5 hours + $50
Evidence3/3 runs agree

What a replacement has to do

  • Create and edit a trip itinerary, place points on a map, share/collaborate the itinerary, and import booking confirmations.

What it still won’t have

  • Large POI database and curated place metadata
  • Deep integrations with booking sites and two-way booking flows
  • Polished native mobile apps and app-store distribution
  • Existing user community and shared guides
  • Proprietary AI features and backend optimizations from the vendor

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying ischeaper in year one.

On cash alone, building overtakes the subscription at 10 seats.

Paid seatsseats

Money you would actually spend

Keep paying

Subscription price × seats × 12

Build it

AI build APIs + hosting

Time you would spend

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal trip-planner web app using Node.js + Express, PostgreSQL, and React. Implement: (1) trip and itinerary item CRUD stored in Postgres; (2) map view with place search using OpenStreetMap/Nominatim (or Google Maps) and save place metadata; (3) a background email-parser worker (simple regex/imap fetch + parsers) to extract booking confirmations and attach them to trips; (4) a route-optimization endpoint that queries distance matrix and returns an ordered day plan; (5) sharing links and basic collaborator roles; (6) expense entries per trip with aggregated totals. Out of scope: native mobile apps, paid third-party deep booking integrations, and machine-learned recommendation engines. Include error handling, retries for external APIs, basic tests (unit + a couple of integration tests), and a Docker-compose dev setup.
How we checked3 sources · 3/3 runs agreed · evidence score 64

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 3 cited sources+3
  • 3/3 assessment runs agreed+4
  • Evidence score64

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time — so the same evidence always produces the same number.

How scoring works →

Cited sources · 3

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! Price not confirmed on the page — this pricing page renders its price in the browser✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat recorded