AI for Editors at Casinos.com
How I trained a bunch of editors to create their own article images
Overview
The editors at Casinos.com had started to use AI to create images for their promotional articles. However their generations were far from on-brand, with crazy compositions and visual errors. Here are 2 examples below…
I was given the task of researching current AI image gen tools with the ultimate goal of training our editors how to better produce images that were on-brand for Casinos.com.
Challenge
Prior to working for Casinos.com I had limited experience working with AI image tools. I had tried Chat GPT and Adobe AI for fun, but I had no idea how to produce images that all shared the same style and looked part of a set.
Objectives
Research: What are the best AI image gen tools out there and which ones would be most suitable and straight-forward for editors to use
Training: LinkedIn Learning courses like Introduction to Prompt Engineering for Generative AI (2023) and Midjourney: Tips and Techniques for Creating Images
Experiement: Figure out how I can produce consistent results that convey the style and mood that Casinos.com branding calls for
Workshop: Create a short training session to give the editors the knowledge and skills they need to start generating images for their articles.
A Quick Video Summary
Below is a video where I presented this project to a group of AI enthusiasts in the wider company I work for. It summaries this project and covers a new process I created for the editors that did not require me teaching them about prompt engineering, but still empowered them to be able to use AI for image generation:
Achieving Consistency
From the courses I did on Prompt Engineering for AI Image Generation, this was the biggest take-away when it came to achieving consistency:
MVP Findings
We saw that customers were really going for this feature, and while it was not the same as a customisable SGP, we saw this activity as confirmation that there would certainly be interest. This meant that whatever resources we were putting into stage 2 were not as much at risk.
Research
Before attempting to design anything I looked at some examples from major sportsbooks that have implemented SGP already. Here are some of my findings:
FanDuel: They have a Same Game Parlay feature available for NFL, NBA, MLB, and Soccer. FanDuel displays individual leg odds and offers a variety of wagers like spreads, moneyline, totals, and more. They also feature SGP-focused promotions and clearly denote eligible games with a green SGP icon.
DraftKings: Similar to FanDuel, they offer Same Game Parlays for various sports. They do not display individual leg odds but allow bettors to see what the entire parlay will pay. DraftKings also enables bettors to combine bets from different games.
BetMGM: Known as One Game Parlay, this platform provides pre-generated 3-leg parlays and a Parlay Builder for custom tickets. The process is streamlined, targeting new bettors with a simple step-by-step guide to creating parlays, though it may lack depth for experienced bettors.
PointsBet: They offer Same Game Parlay for NFL, NBA, AFL, and NRL. While their product is less developed, they do display odds for individual wagers and provide parlay insurance promotions. PointsBet, however, doesn’t clearly indicate which games are eligible for SGPs.
Caesars: Offers a range of same game wagers, especially for the NFL, including various alternative lines and totals, player props, and even unique bets like scoring details.
User Flow
Visually mapping out the steps a user takes to complete the task helps understand and anticipate their journey, and provides a shared language among team members on the project:
Wireframe
Prototype
Prototyping brings ideas to life, allowing for early testing and refinement of designs by Product Owners and QA based on their interactions and feedback
Working with Dev
Involving development early in a project is vital for ensuring technical feasibility and aligning design intentions with practical implementation capabilities, fostering a cohesive and efficient production process.
Testing & Iteration
To ensure a smooth launch of the feature I wrote out every scenario and test script for QA. We discovered a few exceptions that hadn’t been caught in the initial phase like the redundant runner scenario.
Outcome
The data-driven design approach not only addressed a specific user need but also had a broader impact on the platform's success. By catering to the evolving demands of users, the online sportsbook saw increased user engagement, retention, and overall satisfaction. The SGP feature became a key differentiator in a competitive market, showcasing the tangible benefits of a data-centric design approach.
The proportion of parlay bets placed saw a rise in the period measured immediately post launch – 1 month.