Solo Human Architect, Directing an Agent Fleet -- how this system was actually built

One person -- Neel Shah -- directed a fleet of Claude agents to build and validate a production sports-forecasting system across 3,200+ commits (Mar-Jul 2026). He did not hand-type those commits, and he does not claim to have. The role is architect and director: a planner model orchestrates cheaper executor models under hard, automated ship gates that the agents cannot override. The load-bearing human contributions are the ones a fleet cannot supply on its own -- the validation methodology, the ship/reject decisions, and the honesty rails that make an agent's output trustworthy. The share of agent-authored keystrokes (~91%, and rising) is the feature: it is what proves the workflow scaled without the human becoming the bottleneck.

The current-era senior signal is not "can you write code" -- a fleet writes the code. It is whether you can direct that fleet so the output is trustworthy: route work by cost, run executors in parallel without corrupting the repo, and gate every result behind validation strict enough to reject your own best ideas. This repo is the artifact of exactly that skill. The human wrote the gate, the guardrails, and the methodology; the agents wrote the implementation; and the split is recorded in git, not asserted. For an AI-engineering or agent-orchestration role, the honest ~91% is the resume line, not the fine print.