GenAI
GenAI
In this series, I’ve been experimenting with Generative AI — using AI not just as a utility, but as a creative force.
I’ve been exploring the outputs AI can generate, and the products we can build as a result From visuals to sounds and beyond, Gen AI is expanding what we think is possible — unlocking new ways to imagine, create, and build.
🧰 The approach for this series
To build fast and with minimal cost, I’ve been relying on a lean but powerful stack:
From name to features, target users to positioning — I plan to use ChatGPT to get ideas out of my head and into shape fast. It helps me clarify the concept, test different angles, and quickly move from abstract to tangible.
🧠 Step 1 — Flesh out the concept
Tool: ChatGPT
Once the concept is defined, I will use ChatGPT to generate high-fidelity UI screens — using the context we’ve built together in the chat. It usually takes a few iterations, but the results are surprisingly solid.
🎨 Step 2 — Rough designs
Tool: ChatGPT (again)
Lovable is where the concept really comes to life. I will provide a short summary of the product and a few screens, and we would take it from there — turning the concept into a working product, fast.
🔨 Step 3 — Build the thing
Tool: Lovable
Image Gen
Image generation is one of the most familiar and established use cases of generative AI — and has been at the forefront of the AI wave in recent years. Yet despite its popularity, the space continues to evolve rapidly, unlocking new creative and practical possibilities. In this micro-series, I share a set of generative AI concepts — ideas I’ve been exploring and hope to build on further.
Kleinman
A disposable camera app with style
Ancestors
See what your ancestors may have looked like
Video Gen
Video generation is one of the most ambitious frontiers of generative AI — blending visuals, motion, sound, and storytelling into a single dynamic medium. While still in its early days, the space is evolving quickly, with breakthroughs unlocking new creative and expressive possibilities. In this micro-series, I explore generative video concepts — ideas I’ve been playing with as I test the boundaries of what’s possible.
Pensieve
Visualise your dreams as videos or images.
Audio Gen
Audio generation is a fast-moving space within generative AI — from music and voice to ambient soundscapes and even podcasts. As models become more expressive and controllable, new possibilities are emerging for creativity, storytelling, and interaction. In this micro-series, I explore generative audio concepts — experiments with sound, voice, and sonic identity.
Shape Shifter
Reimagine songs with new instruments.
Text Gen
Text is where generative AI first took off — unlocking new ways to write, think, communicate, and create. From content and code to strategy and storytelling, the possibilities keep expanding. In this micro-series, I explore text-based experiments that stretch the imagination and reimagine how we work with words.
Walk with Me
Chat with historical characters.
Mixtape Mate
An chat-based playlist maker.
Mixed Media
The boundaries between text, image, audio, and video are quickly dissolving. Mixed media generation sits at the intersection — combining multiple modalities into richer, more immersive experiences. In this micro-series, I explore concepts that blend formats and channels, pushing the edges of what’s possible with generative AI.
Weave
Weave pieces of content into something new.
