A reliability layer that decomposes an LLM response into atomic claims, checks them against retrieved evidence, and returns a confidence score with the reasoning attached.
Things I’ve built,
and things I’ve written.
Two kinds of work live here. Products I built or shipped, each with the prototype and the write-up on one page. And the writing, where I think out loud about product and AI.
BUILTPrototype and write-up, on the same page.
A music discovery product that ranks on what a song sounds like rather than on how many people already found it.
A controlled test of agent memory: what an assistant writes down when it reflects, and whether any of it transfers.
More coming here shortly.
WRITTENWhere the thinking happens, before it becomes a product.
- Jul 2025 in BootcampThe next chapter in UI/UX: traditional buttons + prompts ↗Prompting moved the interface from think, type, click to think and act. What that costs, what it buys, and why the orchestration behind the box matters more than the box.
- Oct 2024Beyond USPs — User Centric Propositions ↗The unique selling proposition describes the product. A useful proposition describes the user's situation instead, which changes what marketing is for.
- Sep 2024Genshin Impact Through A Product Manager's Lens ↗A long read on gacha monetisation: how the mechanics are constructed, why they work as well as they do, and what a product person should take from that.
- Mar 2021 in Ink & FeatherDoes NSE finally have a good gaming stock? ↗Nazara Technologies' IPO, and whether it gave Indian retail investors a real way into gaming after years of watching the listed studios elsewhere.