Phoenix: AI Creatives Generator

Dentsu, one of the world’s largest advertising networks, continuously seeks ways to combine creativity, data, and technology to deliver impactful campaigns. Scaling content production while maintaining brand continuity, security, and adherence to intellectual property rules is a challenge for South Africa's creative teams. Phoenix, a generative AI-powered tool, was created to solve this issue by improving the campaign delivery and streamlining the creative process.

Phoenix enables customers to create brand-safe, high-quality images using basic campaign inputs. Users receive improved descriptions that are processed by Azure OpenAI's DALL·E 3 after choosing an audience, modifying creative controls like style, intensity, and regional focus, and submitting a campaign description. Cloudinary may then be used to modify the resulting photos for changes like hue tweaks, background removal, and cropping. This process guarantees visual coherence across campaigns, cuts expenses, and lessens reliance on stock photos and human editing.

Technically speaking, Phoenix is designed as a web application that combines several services. Users are guided through campaign configuration, creative development, and authentication by the presentation layer. While the data management layer keeps an audience-builder database and safe user authentication in place, the business layer makes advantage of GPT-based text generating, DALL·E 3 image creation, and Cloudinary editing capabilities. The application's JavaScript frontend guarantees a dynamic, responsive user experience, while the Node.js backend manages user management, secure data flows, and API connections.

In the end, Phoenix shows how generative AI may enable creative teams to produce content in a way that is effective, scalable, and consistent with regulations, as well as simplifying the process from campaign concept to completed, downloadable creative assets.