Sprinklr Ai+ | Ty Eng

Screen Shot 2024-07-18 at 4.13_edited.pn

Project

Creative Ai+

Role

Product Designer

Responsibilities

Enable the ability for social media managers and Ads Managers who don't have advanced design skills to be able to generate and edit images based on text prompts

Use Case

For advertisers utilizing our module, they are primarily looking to generate realistic ads to capture their respective target audience. They would like to do so by either following a Channel, Post, or Placement specific custom prompt or provide a reference image from their repositories to the generator as reference.

As a user

I should be able to generate a series of images based on the text prompt
Generate a new variants of images based on the same text prompt
Able to add a reference image
Able to add effects to an image
Able to discard the options that are not relevant to provide feedback to the system

Challenges

As a team we faced an array of challenges that pushed us individually to create the best user experience possible. Some challenges that were faced throughout this process were:

Design Iterations

Since we were building out an entire new product for Ai, we had to go through many design iterations that aligned with all teams (Leadership, Product Management, Developers)

Dev Constraints

As we continued to collaborate with the UXR and Developers, we had came across many design challenges that arise from constraints on devs end. Collaboration was key in this stage of the design phase, as it shaped out what could be implemented into our Ai product.

UI Elements

As this was a new feature we were designing into our platform, we had faced challenges on how the UI elements were going to appear and provide a streamline experience with the products we currently have.

Competitive Research & Analysis

I had the opportunity to collaborate with our UX Research team on the competitive research and it's primary goal of aiming to evaluate and compare the UX of the leading text-to-image AI platforms. The research was meant to not only dive into primary and secondary use cases, but to identify main personas like Content Creators, and seek to uncover potential new user groups. The insights found culminated actionable recommendations, targeting both functionality and UX enhancements to help facilitate the integration of DALL-E into Sprinklr products.

Designs

After many iterations, challenges, and feedback received, we finalized the designs for our Creative Ai+ that tackles the use cases, and provides an exceptional user experience that is enjoyable and easy to use. Click through the slides to view the UX and see the capabilities our Ai+ has.

User begins their Creative Ai+ journey in the Asset Manager screen, where they click into "Image" to begin utilizing the feature.

User has opened the modal for image asset where they are able to begin inputting a prompt or utilizing shortcuts to create an image generation

User has entered in a text prompt that enables Ai to begin generating their request. This will provide them with 4 useful images to select from

A variety of 4 images populates for you to choose from based off the prompt, which you can either select one or generate more. We also provided an option to select "variants", that render different images to the one you liked.

Once the user has found an image they would like to work with, after clicking "edit", they are directed to the image editor

User clicks into the image where they will see a Ai action bar that allows them to take action with Ai features such as "Generate Text"

"Generate Text" allows them to input any text they would like to appear here, and Ai will provide them will multiple variations for them to choose from

Once generated, this showcases text prompts that are based on what you have input. Users have the ability to click the chevron icon to view different variations.

Another Ai feature we provide for users is "Replace Background". This provides the user to use the same image, but generates new backgrounds to create an exciting new feel.

This example is showing changing the background to daytime, and also provides users with multiple variants of the background.

Generative fill is another feature we provide to our users, that enables to take your image to new heights.

Users begin to draw out where they would like to generate the fill, and enter a text prompt of what they would like to be shown in that particular area.

After inputting the text prompt, users are able to see multiple options.

Next Steps

As we look to build out Ai into many other modules within our platform, the next steps within the Creative Ai framework is to collaborate with my Product Manager and Developer to gain any feedback we have received from our partners. This will help gauge on what is needed to improve the product, and to continue to improve the experience to our users.