Skip to content

Run 1: Avalanche Field Guide

The Challenge

Build a digital backcountry field guide — a polished, interactive HTML page that a backcountry skier could use to prepare for a day in the Wasatch Range.

You're building this entirely by talking to an AI chat tool. No code editor, no terminal — just you, your team, and a conversation with AI. Everything you learned in the lift — the Three Pillars, user stories, the Explore → Plan → Implement → Verify workflow — this is where you put it to work.

Who You're Building For

A backcountry skier planning a day in the Park City / Wasatch Range area. They're checking conditions before heading out. They want to know: Is it safe? What should I watch for? What gear do I need? What do I do if something goes wrong?

They're not an avalanche scientist — they're someone who loves skiing and wants to make smart decisions. Your field guide should make the information clear, visual, and actionable.

What You're Starting With

From the lift, you've got:

  • The Three Pillars (Scope, Intent, Structure) — use them every time you prompt
  • User stories with acceptance criteria — your plan for each piece of the field guide
  • The Explore → Plan → Implement → Verify workflow — your process for building iteratively
  • Right-sizing prompts — small asks in plain English, medium asks as user stories, big asks broken into smaller pieces

Some of you already started building during the lift. In the mob session, your team created a small component — a danger rating display, a gear checklist, or a decision flowchart. You can choose to build from there or start fresh.

Your AI chat tool already knows a lot about avalanche safety, danger scales, backcountry skiing, and the Wasatch Range. Ask it. Explore. Let it help you understand what should go into a field guide — that's the Explore step of your workflow.

Baseline Capabilities

What every team should aim for. You won't finish all of this — and that's fine. Focus on doing each piece well rather than rushing through everything.

  • An interactive avalanche danger scale — all five levels (Low through Extreme) with color coding and a description of what each level means for a backcountry traveler
  • A decision-making checklist that helps a skier evaluate whether conditions are safe enough for their planned trip
  • A terrain assessment section — what to look for, what to avoid, how slope angle and aspect affect avalanche risk
  • Visual design that feels polished — not raw text, but something with layout, color, and structure that you'd actually want to use

Stretch Goals

For teams that nail the baseline and want to keep building:

  • Add expandable or collapsible sections so the guide doesn't overwhelm the reader all at once
  • Create a gear checklist that adapts to conditions — what you need on a low-danger day vs. a high-danger day
  • Build an emergency response section — what to do if someone is caught in an avalanche
  • Add multiple "pages" or a navigation menu that lets the user jump between sections
  • Include terrain-specific advice for the Wasatch Range — popular zones, common hazards, local tips

Tips

  • Start with one section. Don't try to build the whole field guide in your first prompt. Pick the danger scale or the decision checklist and get that right first. Then add the next piece.
  • Use the workflow. Explore → Plan → Implement → Verify. Write a user story for each section before you ask AI to build it. Check the result against your acceptance criteria before moving on.
  • Quick user story template: "As a backcountry skier, I want [what you're building] so that [why it helps]. Given [a specific condition], when [something happens], then [what the user should see]." For example: "As a backcountry skier, I want a decision checklist so that I can evaluate whether conditions are safe. Given the danger level is Considerable or higher, when I view the checklist, then the first item warns me to avoid steep slopes above 35 degrees."
  • Verify criterion by criterion, then be specific. Don't eyeball the whole page and say "looks good" or "make it better." Go through each acceptance criterion — pass or fail. When one fails, say exactly what's wrong: "the danger levels should be color-coded — green for Low, yellow for Moderate, orange for Considerable, red for High, black for Extreme." That specific feedback is what gets you a fix, not a re-roll.
  • If your conversation gets long, start fresh. Remember the oxygen tank — context windows fill up. If AI's responses start feeling off after many exchanges, open a new conversation and paste in what you want to keep building from. You'll be surprised how much better it works.