Hey I'm Sarvesh, An AI native product designer
Hey everyone, I’m Sarvesh, a product designer and builder interested in the space between product design, creative tooling, AI agents, and emerging tech.
Lately I’ve been exploring how AI changes the design workflow, especially around agent harnesses, durable project memory, design systems, prototyping, and how designers can move faster without losing taste or context. I’m especially interested in tools that help builders go from idea to usable product more fluidly.
I come from a product design, advertising, and experience design background, so I care a lot about the bridge between strong UX, creative direction, and technical execution.
Would love to connect with other designers, builders, and people thinking about AI-native workflows.
Twitter: https://x.com/sarveshsea
Portfolio: https://sarveshsea.site
Replies
The durable project memory piece is the most interesting thing for me.
Building as a solo founder with AI tools, the biggest friction I've run into isn't the AI's capabilities. It's that every session starts from scratch. You spend the first 20% of any session re-establishing context that should have carried over from the last one.
I've ended up with a fairly elaborate workaround, essentially a living document that captures every architectural decision, every resolved debate, every do-not-repeat-this lesson. It works, but it's manually maintained, which means it's always slightly behind reality.
Curious what you're seeing from the design side. Are there tools genuinely solving the memory problem, or is everyone still running some version of the manual workaround?