Uxlyze
SaaS · AI analysis · built by Aziz Khan
The problem
Teams guess why landing pages do not convert.
What I built
AI UX and conversion audit: captures screenshots, scores readability, navigation, sections and SEO, runs a Gemini visual analysis and generates a report, with credits and projects in a Next.js dashboard and analysis workers in Go.
Engineering decisions
- The dashboard only writes a report row. A Go worker picks it up, so no web request waits on browser or model time.
- The analyzer drives headless Chrome through chromedp, so the audit sees the rendered page a visitor sees, not an HTML shell.
- Prompts live in a versioned file and Gemini fills a response schema, so the report gets fields it can render instead of prose it has to parse.
- Jobs go through a buffered channel and a per-minute rate limiter, so a burst of reports queues up instead of launching a dozen browsers.
Stack
- Next.js
- Go
- Gemini
- Hono
- Drizzle
- PostgreSQL
Written up in detail
- How to Take an AI-Built App from Prototype to Production
A working checklist for apps built with AI coding tools: secrets, data access, config, payments, background work, deploys and monitoring.
- Why AI Agents Fail in Production and How to Fix Them
Eight ways AI agents break once real users and real data arrive, how to recognize each one, and the fix that holds.
- How Uxlyze audits a landing page with headless Chrome and Gemini
The architecture behind an AI UX audit tool: a Go worker, chromedp, a job queue and structured LLM output.
Need something like this? See AI Integration Engineering and AI Agent Development and AI Deployment & Infrastructure.
More case studies
Have an AI product to ship?
Tell me what needs to be built, fixed, integrated or deployed. You work with me directly, the engineer who reads the code and ships it.