PACE — the Practical Agentic Coding Exam. 800 points, four disciplines, one score that says how good you really are at building with coding agents.
A resume says where you went to school. A LeetCode score measures coding without AI — a skill that's fading. Neither tells you the thing that now matters most: can you get frontier work out of an agent? Right now that's a hunch. PACE turns it into a number.
Not trivia about flags and syntax — the exam scores how you actually drive an agent, drawn from how the best operators work.
Framing a task so an agent can nail it: the right scope, the right constraints, when to plan vs. when to let it run. Can you brief a worker who's brilliant but literal?
The single biggest separator. After the agent changes six files, how do you know it did what you asked — and nothing you didn't? Deterministic checks, diff review, catching the confident-but-wrong.
The biggest driver of cost and quality. Giving enough to decide well, without bloating the window. When to compact, what belongs in memory, what poisons a session.
Parallel sessions, worktrees, skills, orchestration, overnight runs. Turning one operator into a team — the difference between using an agent and commanding several.
Your agent finishes a task and reports all tests pass. You have 30 seconds before a meeting. What's the highest-leverage move?
PACE measures the operator, not the vendor. The skills transfer across every serious coding agent.
PACE is in development. Join the waitlist to sit the first cohort, help calibrate the question bank, and put an early score on your profile.
No spam. One note when the first cohort opens.