Skip to content

Run 2: From Prototype to Product

Where You Left Off

In Run 1, you built an Avalanche Field Guide entirely by talking to an AI chat tool. It looked great — danger scale, decision checklists, terrain tips, visual polish. But the danger ratings likely were made up, the weather may have been fictional, and the whole thing lived inside a chat window.

Then in Lift 2, everything changed. You moved into a real development environment with an AI coding assistant that can read and edit your project's files. You migrated your prototype from chat into the project — it's real now, viewable in a browser, saved and synced. You learned that your code is just files, that version history means you can always undo, and that file access unlocks things chat never could: real data, multiple pages, targeted edits, and team collaboration.

You also did two things that set you up for right now:

  • You wrote user stories during the "Imagine the Upgrade" activity — features that weren't possible in chat but are now possible with file access. Those stories are your starting point.
  • You audited what's real vs. what's hardcoded in your field guide. That audit is your roadmap.

The Challenge

Turn your field guide from a prototype into a product. The big unlock: real data.

Your project's repository comes pre-seeded with real avalanche, weather, and snowpack data for the Wasatch Range. Real danger ratings from the Utah Avalanche Center. Real weather forecasts from the National Weather Service. Real snowpack readings from mountain monitoring stations. Your AI coding assistant already knows this data exists — it can read the files and figure out how to use them.

The moment hardcoded text becomes today's actual conditions is the moment this stops being a demo and starts being something someone could actually use. That's what you're building toward.

As you go, keep building incrementally — one piece at a time, verified before you move on.

Baseline Capabilities

  • The field guide displays today's actual avalanche danger rating for the Wasatch Range — pulled from real pre-seeded data, not hardcoded text
  • Weather conditions are real — current temperature, wind, and forecast from actual National Weather Service data
  • The field guide has multiple pages or sections with navigation between them (forecast, weather, gear, terrain — whatever makes sense for your guide)
  • All changes are saved and synced — your work persists and your whole team can see it

Stretch Goals

  • Add snowpack data — snow depth and trends from the mountain monitoring stations in the repository
  • Make the field guide adapt to conditions — show different guidance for different danger levels (what to do on a Moderate day vs. a Considerable day)
  • Build a trip planning page that combines forecast, weather, and gear recommendations into one view
  • Create a printable trip briefing — a summary someone could screenshot or print for offline use in the backcountry
  • Add visual data displays — a chart of snowpack depth over the past week, a color-coded danger summary, or a wind rose

Tips

  • Start with the user stories you wrote during Lift 2. You already planned this. Pick the one with the biggest impact and implement it first.
  • Use the "What's Real, What's Fake?" audit as your checklist. Each hardcoded item you replace with real data is a clear win. Tackle them one at a time.
  • Ask your AI coding assistant what data is available. Try something like: "What avalanche, weather, and snowpack data do we have in this project? Show me what's there and what I could use it for." Then follow up: "Show me an example of what the danger rating data looks like — what fields are there and what do the values mean?" The more you understand the data before building with it, the better your user stories will be. This is the Explore step of your workflow — applied to data, not just user needs.
  • Save and sync regularly. This is your safety net. If something breaks, you can always go back.