Skip to content
01AI ProductsAug 2026 — Present

Fursa — Visa Route Eligibility

Matches a real profile against official immigration rules and ranks the routes actually open to it — every figure sourced, dated, and priced in the applicant's own currency.

SectorAI Products
PeriodAug 2026 — Present
RoleFounder & Principal Engineer
Delivered viaDinovix Ltd.
01The brief

What was actually broken.

Migration advice is scattered across government pages, forum threads, and agents who are paid whether or not you get in. It goes stale quietly: a fee changes, a quota fills, a route closes, and the version circulating is still last year's. The cost of believing it is not an inconvenience — it is a year of someone's life. Most people who lose that year were eligible for something. Nobody told them the truth early enough, in a language they read, with the numbers as they actually stand today.

02In the product

On screen.

Fursa's home page — the eligibility promise beside a live catalogue of tracked immigration programmes, each with its official source
The promise, backed by a live catalogue
Fursa's problem statement: rules move faster than advice, the real cost is never on the page, and everyone tells you what you want to hear
The problem, stated plainly
03Engineering lens

How it was built.

The architecture, the constraints it was chosen against, and the trade-offs that came with it.

Eligibility is computed in tested, auditable code rather than delegated to a model — the rules are the product, so they have to be inspectable and they have to be right. AI sits around that core, not inside it: two models independently verify each rule against its official government source, and a human signs off before anything publishes. Every statistic on the site carries a link to the page it came from and the date it was last checked, so a reader can audit the claim instead of trusting it. Routes are scored 0–100 across eligibility, affordability, timing, and refusal risk; costs are itemised and converted to the user's currency with estimates explicitly labelled as estimates; timelines are calculated backwards from real intake dates rather than quoted as averages. Built on Next.js on Vercel with Firebase behind it, localised across English, French, and German, with uploaded documents encrypted and deletable by the person who uploaded them.

Stack

Next.jsTypeScriptFirebaseRules engineLLM verification pipelinei18n (EN/FR/DE)Vercel
04Business lens

What it moved.

Measured after delivery, against the numbers the engagement started from.

Destination countries covered
170+
Programmes tracked
1200+
Countries of origin supported
33+