Aydin Aliyev
Bu sayt Azərbaycan dilində də var.Azərbaycanca oxu
Этот сайт есть и на русском.Читать по-русски

Work

My own products, one built with a team, and audits of code that AI wrote. Each entry says what I did and links to the proof.

Showing 6 of 6

  1. RentPilot · Solo build, 2026

    A car-rental marketplace, built by one engineer and an agent team.

    Live at rentit.mobi. About 1,200 commits and over 200 merged pull requests, each one through a review gate I own.

    • Next.js
    • NestJS
    • GraphQL
    • Postgres RLS
    • Playwright
    Evidence: git history, checked 27 Sep 2026

    Read the case study

    RentPilot landing page: “Rent a car you can trust, the moment you land.”
  2. Ta'beer home screen in Arabic: “Did you dream last night?” and an Interpret button.Ta'beer dictionary screen in Arabic.

    Ta'beer · Two-person studio, beta

    A dream-interpretation app whose model may not invent a source.

    Arabic and Sorani, dictionary first. Retrieval is deterministic, the model gets one call, and code rejects any answer that cites what it didn't retrieve.

    • Expo
    • NestJS
    • Claude API
    • Postgres
    • Redis
    Evidence: 200-case eval set, repo docs

    Case study after launch

  3. RedesignAI landing page: “You already built the website. It's just trapped in nine squares.” and a field for an Instagram handle.

    RedesignAI · ALB Group team, live

    An Instagram handle becomes a website; the model writes a plan, never code.

    The model picks from a closed catalogue of patterns and a compiler writes the HTML. A model switch took one benchmark job from 188 s to 46 s, and first-try valid output from 71% to 100%.

    My part: senior engineer and product owner. I rebuilt the generation pipeline and the editor, added the animated progress steps, and built the design kit and templates, all with agentic workflows.

    • Next.js
    • Worker queue
    • Prisma
    • Redis
    Evidence: model benchmark in the repo docs
  4. Audits · Client work, anonymised, 2026

    Two audits of AI-built apps, and what the AI got wrong.

    A Next.js and Supabase app with AI-written summaries: recon, verified findings, a security review and a fix estimate. A payroll SaaS whose founder builds with AI: architecture review, then the fixes.

    Evidence: finding classes and method; the reports stay with the clients

    Classes of finding, first audit

    1. Model output injected into summaries that reach users
    2. A gap in row-level security
    3. Server-side request forgery
    4. Rate limits kept per instance, not per user

    No client names, no specifics until fixed and approved.

  5. GovID · Self-initiated, paused

    A national-ID brief, argued down from a blockchain to a signed, anchored log.

    A red-teamed proof of concept for a digital-identity system. The brief asked for a blockchain; the threat model asked for an append-only log with external anchoring, and that is what I built.

    • TypeScript
    • Postgres
    • Drizzle

    No screenshots: a proof of concept, not a product

  6. Drydock · Own tool, in build

    A one-person research desk where no strategy trades until it passes gates set in advance.

    Crypto research and paper trading with pre-registered statistical gates, a kill switch and an off-host watchdog. An LLM classifies news; it never places an order.

    • 63k-word spec
    • DSR / PBO
    • Paper only

    No profit claims, ever