Engineer, systems-thinker, ships things.

I'm Rishi, a senior engineer with thirteen years of shipping production software, most recently as tech lead of the web team at Adthena, an AI search-intelligence company. There I led web engineering on AIO Signals, part of the AI Overview Dashboard that won at the European and Global Search Awards in 2026; owned the reliability of an extraction pipeline handling millions of events a day; built enterprise single sign-on end to end; and led the design-system migration. I also took AI code review from a multi-week team trial to the standard across the whole engineering organisation, and built the Claude Code tooling my team used for incident triage and release work.

In 2026 I started Tankster AI to work on the problem I kept running into: an autonomous agent is only as trustworthy as the structure around it. So I design that structure and build it by directing AI coding agents: a fail-closed egress proxy that redacts and meters everything an agent sends to a model vendor, a policy gateway for MCP tool calls, and an adversarial harness that judges an agent by what actually changed on disk rather than by what it said. All of it has tests, all of it has CI, and all of it says plainly what it does not do.

I care about the unglamorous things that separate a demo from something people rely on: verification that comes from outside the thing being verified, budgets enforced at a gateway rather than in a prompt, and documentation honest enough to survive a sceptical reader.

A note on where the code lives, because it is a fair question. The infrastructure in the case studies is owned by Tankster AI Ltd and published from its GitHub organisation; the studio runs it in its own estate, and the tools that make agents safe to run are open under MIT while the products built on them stay private. I design each one and build it by directing AI coding agents, which the commit history shows openly. My own GitHub profile is the front door to all of it.