Setting the Scene¶
Maritime Domain Awareness: A Problem Worth Solving
The Houston Ship Channel is the busiest waterway in the United States. Over 280 million tons of cargo move through it every year, carried by more than 8,000 vessel transits per month through a channel that narrows to 530 feet in places. Tankers, container ships, barges, tugs, and offshore supply vessels share the waterway around the clock. At any given moment, a Coast Guard Vessel Traffic Service (VTS) watchstander at VTS Houston-Galveston is responsible for knowing what is out there, what the conditions are, and whether anything needs attention.
The consequences of getting it wrong are measured in lives. On April 13, 2021, the liftboat SEACOR Power capsized in a severe thunderstorm near Port Fourchon, Louisiana. Winds exceeded 80 mph. Thirteen of the nineteen crew members died. The NTSB investigation found that the crew never received the National Weather Service Special Marine Warning for their area. The vessel's NAVTEX receiver, the onboard system that receives broadcast weather alerts, was offline. The warning existed. It was transmitted. It never reached the people who needed it.
That is the core problem: the information exists, but it is scattered across systems that do not talk to each other. The VTS watch floor uses the MTM300 system for AIS vessel tracking and radar, but weather alerts come from NOAA, water levels come from a separate NOAA tides system, and navigational hazards (wrecks, light outages, pipeline operations, rig positions) come from NGA broadcast warnings. None of these feed into MTM300. A VTS watchstander monitoring the Houston Ship Channel has to pull from all of these sources, across separate systems, to build a single operational picture.
Today, you start building the tool that puts it together. Your team is going to build a Vessel Traffic Dashboard: a single-screen operational picture for a Coast Guard VTS watchstander. What vessels are in the area. What ports can service them. What the weather is doing. What the water levels are at channel stations. What navigational hazards are active nearby. Whether any traffic management measures are in effect. One view, one tool, built from real government data sources.
The Houston Ship Channel moves $927 billion in economic activity annually. When the next storm rolls in, when fog closes the channel, when a light goes out on a range marker near a shipping lane, the watchstander's job is to know about it before it becomes a crisis. That is what domain awareness means. That is what you are building.
How the Challenges Work¶
Your team will go through four challenges. Each challenge builds on the last. You never start over. Here's how they work:
- Your team builds one thing together. One project, one demo at the end. For this first challenge, everyone is working in a chat tool, so spread out: each person can experiment, explore different approaches, and get practice prompting on their own. Then come back together as a team, compare what you found, and combine the best parts into one product. Starting in Challenge 2, you'll move into a shared codebase where your team should mob (everyone around one screen) until you have clear swim lanes for parallel work.
- Each challenge builds on the last. What you create in Challenge 1 carries forward into Challenge 2, 3, and 4. You'll add real data, new features, and eventually deploy it live.
- Baseline capabilities and stretch goals. Every challenge has a set of baseline capabilities everyone should aim for, plus stretch goals for teams that get there and want to push further.
- The goal is learning, not finishing. Understanding what you built and why it works matters more than checking every box. Help your teammates. Talk through decisions. Celebrate the wins together.
The Most Important Thing¶
You're about to use AI to build something real. Here's the one thing that will make the biggest difference in what you learn today:
Build one piece at a time.
The temptation will be to write out everything you want in one massive prompt and let AI handle it all at once. Don't. That's not how you learn this skill.
If you paste a wall of requirements and accept whatever comes back, you'll have output, but you won't understand it. You won't know what worked, what didn't, or how to fix it. You won't develop the judgment for when AI nails it and when it needs a nudge. And that judgment is the whole point.
The value is in the back-and-forth. Write a user story. Send it. Look at what comes back. Does it match your acceptance criteria? If not, tell your AI tool exactly what to change. That cycle (prompt, evaluate, refine) is the skill that transfers to everything you'll do with AI after today.
Build incrementally. Verify as you go. Discuss as a team.