Jun '25 - Present
Product Designer via Haus
Product Design, Strategy, UI, UX, Prototyping
Overview
Some details have been generalized and visuals simplified to protect confidential information.
Reduced image turnaround from weeks to minutes by replacing external agency coordination with self-serve AI generation, enabling marketers to create fresh and tailored visuals for every campaign.
01 Prompt-based generation
Describe your idea with just a few words or upload an existing asset to guide AI and create custom images from scratch.
02 Illustration or Photo Realistic
Choose from brand-compliant styles to transform your visuals and match your campaign convincingly.
03 Image iterations
Refine images through natural conversation to remove a logo, change a color, or resize for a different channel without aligning with an agency.
The style selector
The initial direction was a multi-select dropdown with hover previews. I advocated for a different approach since generating multiple styles at once would produce mixed outputs that are harder for marketers to evaluate. Technical constraints validated that single selection would produce clearer, more focused results. I explored three directions and landed on single-select with large preview cards to help marketers make confident choices without extra interaction.
Simplify the metadata panel
From five fields to two. I removed system IDs and file format for the system to handle automatically, and relocated inspiration upload into the prompt area.
Reflection
As part of my workflow, I explored ways to streamline design and development handoffs through new tools and methods. I experimented with vibe coding using Figma Make to speed up implementation, and I explored AI tools for image and video generation such as Kling 3.0, Higgsfield AI, Seedance, Veo3, and GPT 5.
These explorations expanded how I think about the future of creative tooling, helping me design faster, smarter, and more intuitively while staying on the frontier of where AI and design intersect.
