Veranda, a luxury residential concept landing page Veranda is a concept build I created for a fictional luxury residential brand. It is not client work or a real property. The images and hero motion were generated with AI as part of the creative process. I wanted to explore something that matters when building high-fidelity landing pages: after several rounds of changes, how do you make sure the final page still looks like the design that was approved? The site is built in Next.js with responsive layouts, self-hosted fonts, GSAP motion and an interactive walkthrough. I also built in a proper QA process around it, not just checking that the page loads and the buttons work. It compares 12 sections across five screen sizes against approved visual baselines. It flags visual drift, missing baselines and changes that have not been reviewed. I also tested interactions, accessibility, contrast, performance, browser behaviour and reduced-motion states. The main lesson for me was simple: a page can pass functional tests and still no longer be the page that was agreed.

22

26

1.1K

A cinematic portfolio concept for a film and motion studio, designed to feel more like an editorial reel than a standard agency website. The site uses a dark visual system, oversized typography, smooth scrolling, restrained motion, and a full-screen project index to make the work feel premium before the user reads a word. The focus was on pacing, atmosphere and confidence: fewer sections, stronger visuals, cleaner movement. Built as a responsive Next.js prototype with Framer Motion and Lenis-style smooth scrolling, including hero, selected work, about and contact sections.

7

12

495

I built a working AI recruitment screening demo that shows how a hiring team can use AI without handing over the final decision. The flow is simple: A job spec goes in. Candidate profiles are screened against a weighted guideline. Each candidate gets a score, band, evidence quotes, and risk flags. Then everything stops at a human review queue. No auto-rejects. No silent ATS updates. No “AI decided this person is out”. The system includes: Candidate pipeline table Evidence-based screening view Human review queue Approve / reject / snooze decisions ATS deployment plan Audit log for compliance n8n workflow export with a human-in-the-loop Wait node Optional live Claude screening path The important part is the architecture: deterministic logic owns the workflow, gating, state and audit trail. The AI helps with judgement and screening, but the human owns the final decision. Built with Next.js, TypeScript, Claude API, n8n workflow architecture, and a gated ATS sync pattern. This is the kind of system I like building: AI that makes the work faster, but still respects the places where people need control. Shorter Version I built an AI recruitment screening pipeline with a human approval gate. It screens candidates against a rubric, shows evidence quotes and risk flags, then routes every candidate into a review queue before anything reaches the ATS. No auto-rejects. No silent updates. Human-in-the-loop by design. Built with Next.js, TypeScript, Claude API and n8n workflow architecture.

1

139

Cover image for Brands are quietly disappearing from

Brands are quietly disappearing from AI answers, and most of them have no idea. So I built something to make it visible. It is a dashboard that shows how a brand turns up across ChatGPT, Gemini and Perplexity, both where it earns a mention and where it pays for one. You get share of voice per engine, the exact prompts you are winning or losing, and the source each model actually pulled from. The part I enjoyed most was the architecture. The data layer sits behind a clean adapter, so PEEC.AI (http://PEEC.AI), Profound or Semrush slot in with a one-line swap. Mock data runs the demo for now, so the whole thing stands on its own. React, TypeScript and Vite, with a dark console look and a light mode for good measure.

0

105

Idris Lamina

AI Automation & Web Design | n8n · Vapi · Claude API