AggieAirlines

Inspiration

The inspiration for this project was creating a more centralized way of figuring out travel plans. America has one of the most productivity-focused work cultures in the world, which can often lead to burnout. And what better way to deal with that burnout than with recreational travel, but sometimes its hard to know where you want to go. So, we wanted to simplify finding destinations and booking trips.

What it does

This project takes in user-input for a description of what they're looking for and leverages generative AI to come up with a list of destinations and how it might fulfil their desires. After, the user should be given the option to find available flights (using the American Airlines mock-API)based on their destination and the day they want to go.

How we built it

We started off with two members building and testing the backend for API usage in Python while another member began working on the landing page in React. The last member, was working on figuring out a way of connecting the two pieces. When the initial plan didn't work, we switched the backend to Node to (hopefully) make combining together the parts easier. After, we merged together the front and backend branches and began attempting to handle POST request responses on the frontend.

Challenges we ran into

One of the major challenges we ran into was connecting the front and backends. Originally, we had hoped to use python for the backend, however, issues with Django resulted in a migration to Next,js and a subsequent pivot to Typescript in backend. Another challenge we faced was properly sending and receiving payloads from the frontend to display the options in a user-friendly manner.

Accomplishments that we're proud of

We are proud of our flexibility in pivoting technologies when necessary. First, when we realized learning and using Django for our project would be unfeasible in the time provided, we switched over to Next. Second, we planned to use GPT from OpenAI using a provided secret key, but when it failed to work, we switched over to Anthropic. Despite these setbacks, we are proud we were able to quickly pivot without getting overly frustrated and pushed forward with the project.

What we learned

One thing we learned how to do was set up a Node.js server. While some members had tried using similar solutions in other projects, they had little success, so none of us understood how to properly set up a Node server. Another thing we learned was how frustrating Javascript can be to work with.

What's next for TamuTravel

Next steps for TamuTravel include expanding the location offerings to more than just select cities in the United States (based on the mock American Airlines API). As well, we hope to connect the application with a form of push-notifications to give users real-time updates about their travel plans (such as recorded flight delays or inclement weather at their destination during their stay).

Built With

• american-airlines-api
• claude
• next.js
• node.js
• rust
• typescript