Skip to content
Page 8 of 10

Challenge 1: Vessel Traffic Dashboard

What You're Starting With

From the lesson, 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 dashboard
  • 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

Maybe you already started building during the lesson: a vessel status board, a weather summary, or a quick conditions display. You can choose to build from there or start fresh.

The Challenge

Build a Vessel Traffic Dashboard: a working prototype that gives a Coast Guard VTS watchstander an operational picture of the Houston Ship Channel.

The Houston Ship Channel handles more tonnage than any other waterway in the United States. Tankers, container ships, tugs, barges, and offshore supply vessels share a channel that narrows to 530 feet in places. A watchstander's job is to know what is out there, what the conditions are, and whether anything needs attention, all at once, all the time.

But what does "needs attention" actually mean for vessel traffic? What makes a situation routine versus concerning? What kinds of conditions affect operations? Those are questions worth exploring before you start building. Your AI chat tool knows a lot about vessel traffic management. Ask it. The more you understand the domain, the better your prototype will be.

Who You're Building For

A Coast Guard Vessel Traffic Service watchstander at VTS Houston-Galveston. They sit on a watch floor monitoring 70+ miles of restricted waterways: the Houston Ship Channel, Galveston Channel, Texas City Channel, and Bayport Ship Channel. On a typical day, 50+ deep-draft vessels, 400+ tugs, and 600+ barges move through their area.

Their job is to know, at any moment: what vessels are in the area, what the conditions are, and whether anything needs attention. Right now, that information comes from multiple separate systems. Your dashboard starts bringing it together.

What to Build

This is a prototype: you're exploring what works, not building a final product. The goal is a dashboard that a watchstander would look at and say, "yes, this is the kind of thing I need."

  • The watchstander can see the traffic picture: what vessels are in the area, what they're doing, and how the channel looks overall
  • The watchstander can tell at a glance which vessels or conditions might need attention, so they can focus where it matters instead of scanning everything equally
  • The prototype is something you could show to a watchstander and they'd recognize it as useful for their job

These are options for teams that want to push their prototype further. Your team can also define your own stretch goals. Use the Explore step to research what else a VTS watchstander needs, then build toward it.

  • The watchstander can assess how weather or conditions affect the vessels currently in the channel
  • The watchstander can evaluate whether nearby ports have what a specific vessel needs
  • The watchstander can get a complete operational brief from one view, enough to hand off to the next watch
  • The watchstander can answer "what do I need to know right now?" without piecing it together from separate sections

In Your AI Assistant

If you didn't get a visual prototype: AI tools respond differently each time, even from the same prompt. Try these in order:

  1. Look for a Preview, Play, or Run button in your tool's interface. Claude.ai, ChatGPT, and Gemini can all render live previews, but you may need to click a button to switch from code view to preview. Some tools require you to be logged in.
  2. Look for Canvas mode. Some tools have a side-by-side view where you chat on one side and see your prototype on the other. In Gemini, click the + button below the prompt box and select Canvas. In ChatGPT, look for a Preview or Canvas option.
  3. Did AI give you code to install, a download link, or setup instructions instead of a visual page? Ask: "I don't want to download or install anything. Can you turn this into an interactive prototype I can see and use right here in our conversation?"
  4. Got HTML code but no live preview? Click Download code above the code block, or copy the code into a plain text editor (like Notepad or TextEdit), save it with a .html extension, and open it in your browser.
  5. Still stuck? Start a new conversation, or switch to a teammate's machine. Don't spend too much time troubleshooting.

Tips

  • Don't know the domain? That's what Explore is for. Before you start building, ask your AI chat tool about the domain. Try: "What does a VTS watchstander need to monitor in a busy shipping channel? What situations require them to issue a traffic advisory? What makes traffic conditions concerning versus routine?" The answers will shape what you build. The more you understand the watchstander's world, the better your dashboard will be.
  • Start with one capability. Don't try to build everything in your first prompt. Pick one thing the watchstander needs, build it, verify it works, then add the next piece.
  • Use the workflow. Explore, Plan, Implement, Verify. Write a user story for each capability before you ask AI to build it. Check the result against your acceptance criteria before moving on.
  • Quick user story template: "As a VTS watchstander, I want [what you're building] so that [why it helps]. Given [a specific condition], when [something happens], then [what the watchstander should see]."
  • 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.
  • 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.

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.