Tailwind evolved out of a desire to create a digital docent: someone to guide visitors to works in the museum's collection and help them experience the art in a holistic, inclusive way. We wanted to create an app that was simple in design and a powerhouse behind the scenes: one that would allow visitors to the PMA to have a rich, engaging experience directly with the objects on display by way of an easy-to-use, personalized guide.
What it does
Tailwind suggest objects for a visitor to view, gauges the visitor's response to a particular object, and suggests other pieces based on the visitor's reaction, in addition to the reactions of other visitors with similar profiles. The app also includes fun activities for visitors to participate in, which helps visitors engage with the works in the museum's collection.
How we built it.
Tailwind was an exciting challenge for our team, as it enabled us to use skills we already had in addition to learning some new skills. For example, this is a first-time Swift app for anyone on the team.
Tailwind utilizes a custom API which extends the PMA API functionality in order to create a more robust experience for app users.
In order to create personalized experiences for PMA visitors, we created a recommendation engine, powered by Python/Django. First, the app assigns visitors a team, based on their answers to five onboarding questions. Once a user is assigned to a team, the app recommendations a few pieces of art, based on core characteristics of that visitor's team, and what previous members of that team have responded positively to. The recommendation engine is fed by user responses in the form of emojis, which enables the app to create better future recommendations.
We also implemented the use of the PMA mobile framework and Apple Indoor Positioning System, which triggers specific activities to present themselves to visitors, giving visitors opportunities to engage with the artwork in a more holistic way.
We also were particularly careful about inclusivity in our app design and content. Whenever possible, we asked visitors to "move" through the space, rather than "walk." We also chose color contrasts and text sizes that are compliant with Web Content Accessibility Guidelines (WCAG) 2.0. We wanted to create our app according to best practices to make it as accessible as possible.
Challenges we ran into
We wanted Tailwind to be a fun, inclusive app, that encourages visitors to interact with, contemplate, and think about the PMA's collection, and make connections to the art and their personal lives. We ran through many user flows and ideas about how the app would look and feel. The major challenge here was that, while we wanted to create a personal digital docent, we also wanted to keep the app simple and elegant, both to match the PMA's aesthetic, and to encourage visitors to engage with the art more than with the app. After all, our goal was to make the art sing for visitors, and allow them to experience the work on their own terms. This proved to be a fun challenge for the team, as we pulled together to figure out how visitors could utilize our app to enhance their visit to the PMA.
Accomplishments that we're proud of
In addition to creating our first Swift app, we are super proud that we were able to combine a recommendation engine that builds a personalized tour for visitors with a location-based series of close-looking and art appreciation activities to drive engagement with the collection.
What we learned
User flows are quintessential to a successful app! Because our app utilizes multiple technologies in order to answer the PMA's prompt, we needed to create user flow after user flow to make sure the experience of using the app is simple and elegant.
Iterating our user flow kept our team communicating well. It was our blueprint for the app from beginning to end. Regardless of our specific role in production, the user flow kept us on the same page about how Tailwind functions at every step of the journey.
What's next for Tailwind
We hope to continue working on Tailwind to refine the experience for users. Because the recommendation engine relies, in part, on user responses, we hope to test the app with PMA visitors to feed the engine. The app is scalable and requires little work on the museum's end to customize the experience, so we would love to be able to take this model into a variety of institutions.
Try it yourself!
Visit http://museumcrawlers.com to take the test!