You'll DESIGN, BUILD, and TEST your own human-AI interaction system.
This is a team-based, half-semester-long design project, in which you'll create an original human-AI interaction system on your own. You can pick any kind of system that you learned in this course, e.g., recommender systems, emotion detection systems, data visualization systems, and many more. You'll work in teams of three people. More information about each milestone will be added to this page. Here is the timeline and grading weights for each milestone:
Now that you learned the importance of human-centered design and the importance of harnessing the power of AI to create smart system for people, it's a good step forward that you apply what you learned to a problem you deeply care about. It's a great way to learn further, and potentially make impact.
We'll create an assignment in KLMS for each milestone.
For each milestone deadline, all members of your team will lose 10% for each late day. Submissions will be accepted until three days after the deadline. After then you'll get 0 on that milestone. Please note that late submissions for final presentations are not allowed.
You'll need to find teammates to work on an exciting project for the rest of the semester. Each team should have 3 people by default. In exceptional cases we'll accept 4-person teams.
Here are three methods you can use:
Please fill out the design project sign-up form.
In a team, you'll identify a problem that you'd like to tackle with your project, and brainstorm approaches to solving the problem. After you've identified an interesting problem, a set of concrete tasks you want to support, and a set of possible solutions, it's time to turn these into a convincing pitch!
You'll have 10 minutes to do the following:
After the pitch, you'll have three minutes for Q and A.
Note #1: We'll enforce a strict 10-minute time limit by cutting off the presentation. Please plan and rehearse.
Note #2: Note that all team members should present at least once between the pitch and the final presentation. This means if your team decides to have only some members present in the pitch, the remaining members should definitely present in the final presentation.
You'll present in class and submit your slides after the class, which are due 11:59pm on the day of presentation.
Your team's slides should be submitted as a PDF file, via KLMS.
Now's the time for a fully functional and interactive prototype that is ready to be tested by your target users. You need to build a prototype that supports end-to-end scenarios. Your prototype needs to support at least three distinct tasks. This does not mean you need to build three separate prototypes, but rather this means you need to build one complete prototype that is flexible enough to support the three tasks. You may choose to reuse or revise the tasks and the UI you created in earlier stages. Make sure your tasks are centered around novel human-AI interaction you intend to support. Other features (e.g., detailed my page design, complex login management) can be hard-coded or fed with fake data.
Your report should include:
One report per team. Your report should be submitted as a zip file. The instructions should be written in Markdown (please use the .md extension). Submit using KLMS.
Now that you have an awesome prototype, it's time to tell us about what you built and what you learned from having real users use the system.
You'll have 7 minutes to do the following:
Note #1: We'll enforce a strict 7-minute time limit by cutting off the presentation. Please plan and rehearse.
Note #2: Note that all team members should present at least once between the pitch and the final presentation. This means if your team had only some members present for the pitch, the remaining members should definitely present for the final presentation.
Here's how your pitches will be graded.
You'll present in class and submit your slides after the class.
Your team's slides should be submitted as a PDF file, via KLMS.
Now that you have deployed your system, seen people use the system, and collected useful data, it's time to wrap it all up! You'll write a short report and make an engaging video that showcases your system.
Record a 2-minute video that captures the user context and the killer features of your UI. Be creative in how you plan, structure, and record the video! Check out project gallery for inspiration. You need to set the stage by starting with users and their problem. Avoid using slides and try to capture realistic context, and don't hesitate to "act". Do not show the UI from the beginning. You need to show parts of your final prototype to demonstrate how the user might perform the task using your system. Rather than describe all the features you implemented, focus on the flow of the task.
NOTE: Make sure to connect the user scenario and the solution. A common antipattern is to make the UI description too generic, not about solving the particular user problem captured earlier in the video.Here's how your report will be graded.
Part 1: Report (10% toward your project grade)
Part 2: Video (10% toward your project grade)