Where I turn ideas into working software fast, with AI as my pair — and test design decisions in real interfaces instead of mockups.
Research with AI
I start by using AI to research the problem, the people it affects and what already exists, before I design or build anything.
Design
Then I design the flows and the interface myself. I decide what to build and why, and let AI draft it.
Validate
I test it against what the research found and put it in front of users, and I fix what does not hold up.
Release
Then I ship it. A working product in real hands teaches more than another round of mockups.
Velobotix
Client: Revwald (Pvt) Ltd.
A one-line pitch for what this does and who it's for.
Replace this with two or three sentences: the problem you noticed, what you built, and what makes it interesting. This card is a placeholder that shows how a project will look.
A product is only useful if people and machines can find it. Alongside design, I make sites easy for search engines, answer engines and AI assistants to read, understand and quote.
Google Search Console
Setting the site up in Search Console, submitting the sitemap and checking how Google indexes the pages.
Bing Webmaster Tools
The same for Bing, whose index also feeds other search engines and AI assistants.
Semantic element changes
Replacing generic markup with semantic HTML: real headings, landmarks and lists, plus structured data, so the page structure is clear to machines.
Content write-ups
Writing clear, answer-first copy: page titles, descriptions, FAQs and case-study text that serve the reader and the search.
LLM-readable text
Plain-text versions of the site (llms.txt and llms-full.txt) that AI assistants can read and cite accurately.
Open Graph
Open Graph and Twitter card tags, so a shared link shows the right title, description and image.
This portfolio uses all six. View its source to see them at work.