Skip to content
Page 5 of 6

Challenge 3: Context-Powered Iteration

Recap:

In Challenge 2, you turned your app from a prototype into a product. Hardcoded sample data became real data from live sources. You added pages, navigation, and polish, and everything was saved and synced so your whole team could see it.

Then in Lesson 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 Challenge 1, you explored the domain and built a prototype. In Challenge 2, you connected real data into a persistent application. In Challenge 3, your dashboard goes from displaying information to making assessments.

What does that mean? Right now, your dashboard shows data: vessels, conditions, maybe port information. But a VTS watchstander doesn't just look at data. They interpret it. When water levels drop, they check which vessels draw too much for the current depth. When weather deteriorates, they figure out which vessels are in the affected area. When visibility drops below a threshold, they consider restricting traffic. Those are assessments, and your dashboard can start making them.

Your project context file is what makes this work. When you add domain rules to the context file ("when water levels at a station drop below a certain threshold, flag deep-draft vessels in that section of the channel"), your AI coding assistant follows those rules when it writes code. The more rules you add, the smarter the software it writes. Every new conversation builds on those rules automatically.

What rules should your dashboard follow? That's worth exploring. Ask your AI assistant: "How does a VTS watchstander decide when to restrict traffic in the Houston Ship Channel? What conditions trigger that decision?" The answers become the domain rules you encode in your context file, and those rules shape every feature your AI assistant builds.

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

What to Build

  • 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
  • Draft clearance assessment: the watchstander can see water levels at channel stations compared against vessel requirements, so they know when depth may be insufficient for specific vessels in the area
  • Weather-impact assessment: the watchstander can see which vessels are in areas where weather alerts are active, so they can issue advisories before conditions get worse
  • Domain rules live in your context file: the operational rules behind your assessments are captured in the context file so that every conversation your AI assistant uses them when writing code

These are options for teams that want to push further. Your team can also define your own stretch goals. Use the Explore step to research how VTS watchstanders make operational decisions, then build assessment capabilities that support those decisions.

  • At least one additional condition-based assessment beyond clearance and weather: traffic management triggers, navigational hazard proximity, or something your team discovers through exploration
  • Conditions risk score: a triage rating system that gives the watchstander a quick way to see which situations are highest priority. When multiple things need attention, the rating tells them where to focus first.
  • The watchstander can see when conditions may warrant traffic management measures, based on rules defined in the context file
  • A conditions-based shift briefing that adapts to current data and highlights what the incoming watch needs to act on first

Tips

  • Start a fresh conversation first. Make sure your context file is doing its job. Ask: "What is this project and what data do we have available?" If AI knows, you're good. If it doesn't, fix the context file first.
  • Update your context file as you build. When you add a domain rule, a new assessment, or change how the app is organized, tell your AI assistant to update the context file. A quick "Update the context file to include what we just built" keeps future conversations sharp.
  • Domain rules are where the intelligence lives. When you want the dashboard to assess a condition, encode the rule in the context file. Your AI assistant uses those rules when it writes code, so the software follows them automatically. The threshold is your decision. Research what makes sense: "What's a normal water level range at Houston Ship Channel stations, and when do low levels start affecting vessel transit?"
  • Ground assessments in real conditions. AI can generate logic that sounds right but uses wrong thresholds. When the dashboard flags something, trace the logic back: what data triggered it, what rule applied, and does the threshold make sense?
  • Save and sync often. You know the drill.

Go build. That's the brief. Spend the rest of this session block working on your challenge with your team. Your Facilitator will let you know when it's time for the Reflection.

Our recommendation: mob until you have clear swim lanes. Think of your project like a shared document. If two people edit the same section at the same time, their changes collide and someone's work gets overwritten. The safe way to split up is clear swim lanes, where each person works on a different section. Until your team has those lanes, mob: one person drives, everyone else navigates. Rotate every few minutes. One keyboard, zero collisions.