Skip to content

Inca Trail

Helping travelers plan the Inca Trail without selling them a tour.

I’ve been visiting Cusco for years. As a Peruvian living in New York, it’s a place I know well.

A hiker on a mountain trail in the Andes

What always bothered me was how difficult it was to find independent information about the trek. Most search results led to tour operators selling packages. Prices weren’t always clear, recommendations were often promotional, and useful information was scattered across dozens of websites.

I already owned incatrail.com, and I’d been sitting on the idea for years.

So I decided to build the resource I thought should exist: a free, independent planning guide that helps travelers understand their options before choosing an operator.

incatrail.com
Role
Product designer, builder
Timeline
2026
Models
Claude (development and research)
Status
Public guide preview; expanded permit and operator platform in development

01 / ORIGIN

Building a guide, not another sales funnel

I’ve spent years visiting Cusco, but researching the Inca Trail online still left me frustrated. So much of the information came from tour operators selling packages that it was hard to separate useful guidance from a sales pitch.

I already owned incatrail.com, and I wanted it to serve a different purpose: a free, independent guide that helps people understand the trek before choosing a licensed operator.

02 / EXPERIENCE

Putting the planning before the booking

Planning the Inca Trail comes with a lot of questions. Which route should I take? How difficult is it? When should I go? What permits do I need?

I organized the experience around answering those questions, rather than steering people toward a purchase.

Travelers can compare eight routes, explore the Classic Trail day by day on an interactive map, and find permit information in one place.

The goal is to help someone approach an operator knowing what they want and what to ask.

03 / DECISIONS

Making trust part of the design

When someone is planning an expensive trip from another continent, inaccurate information can become a real problem.

During design reviews, I found copy promising hourly permit updates, accreditation badges we couldn’t verify, and numbers that looked real but weren’t connected to actual data.

I removed or corrected those claims rather than letting a polished interface imply capabilities we didn’t have.

I also chose not to put AI into the visitor-facing trek finder. A transparent scoring system was easier to explain and more appropriate for the decisions travelers needed to make.

IncaTrail.com has a researched public guide, eight trek routes, and an interactive Classic Trail explorer.

A larger platform for permit tracking, operator profiles, and traveler inquiries is designed and partially built, but isn’t being presented as finished.

The challenge now is completing the operational work and verifying the information needed to make that next layer genuinely useful.

I want the site to become a resource travelers trust, even if they never book anything through it.

From idea to production, with AI as a collaborator.

Glossy black robot character with glowing eyes

Discover

Understand the problem

  1. Step 1: Frame the idea

    Problem, audience, desired outcome

  2. Step 2: Explore together

    Questions, alternatives, tradeoffs

  3. Step 3: Validate assumptions

    Research, feasibility, evidence (AI research - I decide)

Define

Set the direction

  1. Step 4: Define the product

    Requirements and success criteria

  2. Step 5: Plan the work

    Milestones, tasks, acceptance tests. AI drafts

  3. Step 6: Approve the plan

    I revise scope before work begins. My approval.

Deliver

Build, verify, release

  1. Step 7: Build + review loop

    Implement, agent audit, fix, recheck (AI and agents)

  2. Step 8: Connect + test

    Services, env setup, staging QA

  3. Step 9: Ship + learn

    I approve release; we iterate. My approval

I use AI throughout the product development process, from exploring an idea and challenging assumptions to defining requirements, building, and reviewing the implementation.

But I don’t want a model that simply agrees with me. I expect it to question decisions, identify tradeoffs, and provide evidence that the work actually functions.

I review the plan, direct the experience, and use independent agents to help verify the implementation. Before release, I test the product and make the final call.

AI makes it possible to move much faster. My responsibility is making sure we’re moving in the right direction.