Skip to content

Run 3: Context-Powered Iteration

Where You Left Off

In Run 2, you turned your field guide from a prototype into a product. Hardcoded danger ratings became today's actual conditions from the Utah Avalanche Center. Made-up weather became real forecasts from the National Weather Service. You added pages, navigation, and polish — and everything was saved and synced so your whole team could see it.

Then in Lift 3, you hit the wall: every new conversation meant re-explaining your entire project from scratch. You learned why AI forgets between conversations, and you solved it. Your team wrote a house-sitter note, turned it into a real project context file, and tested it — AI knew your project without being told.

You also practiced two ideas that matter right now:

  • Table of contents, not the whole book. Your context file is short and points to your project's documentation — it doesn't try to contain everything.
  • Start fresh for fresh eyes. When a conversation gets long, start a new one. With the context file in place, starting fresh costs you nothing — AI picks up right where you left off.

The Challenge

Your AI coding assistant knows your project now. Every conversation starts with context instead of confusion. That changes everything about how fast you can build.

In Run 1, you were learning how to talk to AI. In Run 2, you were learning how to work in a real project. In Run 3, you're just building — and context is the reason you can move this fast.

Time to be ambitious. Your field guide has real avalanche and weather data. Now push it further: snowpack conditions from mountain monitoring stations, safety recommendations that change based on today's danger level, a trip briefing you could take into the backcountry. The exact direction is up to your team — context makes iteration fast enough to go wherever your ideas take you.

Build incrementally — one feature at a time, verified before you move on.

Baseline Capabilities

  • Your project context file is working — start a fresh conversation and verify that AI knows your project, your data sources, and your design without you explaining anything
  • Snowpack data is part of the field guide — real snow depth readings from mountain monitoring stations in the Wasatch Range, showing recent trends (your repository already has this data — ask your AI coding assistant what snowpack information is available)
  • Condition-specific recommendations — the field guide gives different safety advice depending on the current danger level (what's safe on a Moderate day is very different from a Considerable day)
  • At least one team-chosen feature — something your team is excited about, whether it's from the stretch goals below or an idea of your own

Stretch Goals

  • Printable trip briefing — a summary page that combines today's forecast, weather, snowpack, and gear recommendations into one view someone could screenshot or print for offline use in the backcountry
  • Adaptive gear checklist — gear recommendations that change based on current conditions (a Low danger day calls for different preparation than a High danger day)
  • Trend display — show how danger levels or snowpack depth have changed over recent days, so skiers can see whether conditions are improving or deteriorating
  • Red flags — automatically highlight the most critical safety concerns from the forecast data (specific avalanche problems, dangerous elevation bands, problematic aspects) so the most important information jumps out first
  • Route planning helper — let the user pick a zone, aspect, or elevation band and see tailored conditions and advice for their specific planned route

Tips

  • Start a fresh conversation first. Before you build anything, open a new conversation and make sure your context file is doing its job. Ask your AI coding assistant: "What is this project and what data do we have available?" If it knows, you're good to go. If it doesn't, fix the context file first — everything else in this run goes faster when context is working.
  • Update your context file as you build. Tell your AI assistant to update the project context file when you: add a new data source (like snowpack), add a new page or section, change how the app is organized, or make a design decision you want AI to follow consistently (like "always show danger level colors"). A quick "Update the context file to include what we just built" takes seconds and keeps future conversations sharp.
  • Try the discovery prompt. When you're ready to add snowpack data, try: "What snowpack data do we have available in this project? Show me what's there and suggest how we could display it in the field guide." Let AI explore for you.
  • Ground safety recommendations in real sources. When AI generates advice like "avoid slopes above 35 degrees on Considerable days," check it against what the Utah Avalanche Center actually says. AI can phrase things convincingly but get details wrong — and for avalanche safety, wrong details can be dangerous. Use AI to build the feature, but verify the safety content against authoritative sources like utahavalanchecenter.org.
  • Save and sync often. You know the drill — this is your safety net. Save after every feature that works.