This edit started with a simple challenge: several different creators, different deliveries, different footage, but only one short ad to make it all feel cohesive.
The first step was finding the strongest soundbites and figuring out how they could work together as one story rather than feeling like a compilation.
From there, I built the structure around a clear hook, fast progression and a product-focused payoff, then used captions, product inserts, motion, transitions, music and sound design to keep the pace moving without losing the natural UGC feel.
What I enjoy most about this kind of edit is that the real work happens before the polish.
It is deciding which sentence opens the video, which reaction is worth keeping, when to change creator, when to show the product, and how to make every cut feel intentional.
The goal was to keep the authenticity of UGC while giving the final piece the rhythm and clarity of a paid social ad.
1
198
A dark-mode study platform for medical and nursing residency candidates: lessons, question practice, flashcards, mock exams and performance analytics in one place.
The goal was to make the next step obvious. Every screen leads with a single action, and progress is always visible, rings, streaks and history charts that turn effort into something you can see.
What do you think?
3
9
417
This is a motion design project we created before generative AI tools really took off.
The video presents an auto claims assistance platform, connecting people who had their car damaged with specialists who can help solve the problem.
Today, with AI, we can create more ambitious things and explore visual directions that would have been much harder before. But I still really enjoy this kind of full motion project.
0
140
This project started with a very specific idea for how a static product visual should move.
The base artwork was created with ChatGPT and Nano Banana, but before generating the final animation, I spent time refining the prompt and defining the exact movement, camera behavior and energy we wanted.
I tested the direction with different models, including Kling 2.5, using those iterations to improve the prompt before producing the final sequence with Seedance 2.5.
The result was extremely close to what we had planned, including the animation and even the sound effect that completed the motion.
For me, this is where AI production gets interesting: the real work is not simply generating. It is art direction, prompt design, testing and refinement until the model delivers the intended result.
17
26
945
