Rajeev Gill
My work sits between product thinking and implementation, with a bias toward systems that make real work less messy.
Based in London. Interested in useful AI, clearer measurement, and software that holds up outside a demo.
Get in touchSelected projects
A measured field guide to every local model installed on Apple Silicon.
A transparent guide to open-source go-to-market software.
A production-ready single-screen judging app built for a live hackathon room.
Recent writing
My coding agent kept waking up to ask GitHub whether CI had finished, and every wake-up dragged the whole conversation back through the model. An audit found 612 wait-only responses and about 77.75M raw tokens. The fix: hand the waiting to CI, and let the agent stop.
How I use ChatGPT as the controller, a private GitHub control repo and an Actions-dispatched Mac runner as the delivery path, and OMP/GLM as the cheap execution worker — including what broke in the first real end-to-end test.
A decision playbook for running Codex subagents without token cost surprises — when to delegate, how to bound each worker, and how to measure what it actually cost. Built from three measured experiments on this site.
I am always interested in thoughtful software, analytics, and AI work where the practical details matter.
Email me