Who's behind Surau.

The idea for Surau didn't begin with a technology. It began with a discomfort I couldn't shake. We now ask AI about everything — including the most personal, sacred parts of our lives. It answers instantly, fluently, with total confidence. But ask it where the answer came from, and the confidence falls apart.

I studied at Al-Azhar in Cairo before choosing to stop and focus on building digital products. Those two worlds — classical texts and product-making — meet in Surau. From the very first sketch, the product had one job that everything else would serve: never let someone believe an answer they can't verify.

So I designed for verification, not just information. I also designed for refusal — on purpose. A product about faith that confidently invents an answer is worse than one that honestly admits a limit. Making 'I don't know' feel like integrity rather than failure was a deliberate design decision.

Shipping the wrong thing fast is still shipping the wrong thing.

I built an editorial workflow — draft, review, publish — so nothing reaches a reader unreviewed. Then I brought in a friend, an Al-Azhar graduate with experience in the relevant field, to review the data. The machine makes sure nothing ships unreviewed; a person makes sure what's reviewed is actually right.

I also learned to read the negative signals — the expensive way. I once let a process burn far more resources than it should have, and paid roughly twelve times over for that lesson. After building retrieval that genuinely worked, I did the honest math on running it at scale — and as a solo builder, the numbers didn't close. So I paused that part: not because it failed, but because forcing a product that only survives if I ignore the numbers would have been ego, not sense.

So I changed the order. Instead of clever retrieval on shaky data, build the clean, verified library first — starting with the Quran, on an official, government-published foundation — and earn the right to retrieve over it later. Slower, but it's the only sequence that produces something a person should actually believe.