Sawa-design automation
Sawa, a design tool operating by identifying a set of familiar graphic design practices and then developing an interactive system of suggestions based on these practices. The outcome consists of three contiguous steps: Setting Constraints, examining Variations and Iterating through compositions.
the landscape
A sense of progression. Design tools like Adobe Suite have made graphic design ubiquitous and accessible to a much wider audience. They represent initial technological advancements that automate the process of designing.
... reflecting
Progressing, even further. Lowering barriers with precision alignment tools like visible grids have allowed even more people to render ideas effectively. However, mastering the software is still a major challenge.
templates
Early attempts. Templates have been offered as a solution to absolve the designer of these issues. They allow those not as skilled in design to create a professional looking product, because a designer created the template, and all the next person did was fill it in with their own photos or text.
temp-late
Templated fixes. The result of templates is a lack of identity. Most users find this problematic, as most brands do not want to look like other brands. This issue has evidently been acknowledged with the advent of suggestive interfaces, even within tools like Keynote and adobe.
sawa
Moving beyond templates. Sawa proposes a system by which we can further assist anyone in developing uniquely tailored design outputs. This proposal relies on the notion of Suggestions as a tool to improve the design process.
proposal
Suggestions can exist in multiple forms: Variations, a set-of distinct, alternative solutions to a given problem at a point in time. Iterations, versions of the same solution at different points of revision.
interface architecture
First steps. In crafting the system-architecture, we begin by primarily adopting common graphic design principles that decisively inform suggestion shown.
Additionally, in outlining a user-flow, for a tool that assists people in the design process, it seemed natural to look inwards at the common design practices and processes that design practitioners use.
constraints
Freely Constrained.
We deliberately begin the process by allowing anyone specify their intent. Specifically, anyone can define the dimensions of the canvas. These are initially explicitly specified but later inferred from user behavior over time.
Even as designs progress, the system steadily accounts for any given constraints
We infer constraints such as alignments by using guide-lines whenever items are adjusted but also explicitly allowing for users to re-specify canvas dimensions at anytime, without ruining on-going designs.
variations
Organically Unique, anytime.
Thinking different, first. The system begins the design process with a set of design compositions, taking already existing images stored on the platform and then showcasing variations in representation. Each composition is structurally different in both style and layout options.
Along the way, if one decides diverge and explore alternative designs with the same content, the system responds with diverging choices that vary in symmetry, type, graphical size, alignment preferences, and much more.
Alternatively, simply pinching to zoom out showcases variations. The system assumes that variations exist on a randomized canvas that implies variety. Much of this came about after many iterations that allowed us to
iterations
Continuous Refinement.
Iterations represent small incremental changes for the same composition. The system acclimates to user inputs, generating new iterations as changes are made to compositions.
Specifically, these refinements do not add any new components or make any grand changes; but rather we default to subtle, potentially relevant tweaks to refine ideas even more.
These choices are intentionally chronologically arranged in order of the intensity with multiple options in view to allow for comparison.
reflections
The purpose of this work was to help provide informed-direction to product managers and executives. Some of the foundational theories presented in this project resulted in the launch of The Creative Assistant, Mailchimp's first AI creative tool.
“Thank you so much. My team was raving about you after our meeting. You’re a beast - this looks fantastic, thanks for the reference.”
Francis T.
Senior Product Manager, Mailchimp