AX, agent experience, is how well a codebase or tool is set up for an AI agent to work inside it. It is the newer sibling of DX: the same instinct to remove friction, aimed at the agent rather than the human. As more work runs through agents, AX is quietly becoming something teams design for on purpose.
What good AX looks like
An agent has no intuition about your project. It learns everything from what it can read, so the codebase itself has to teach it. That means clear structure it can navigate, an AGENTS.md that states the conventions and commands up front, and skills it can load for specific tasks instead of guessing.
It also means feedback the agent can act on without a human. Fast tests, a type checker, and other automated checks give the agent a signal to iterate against, which is the difference between an agent that self-corrects and one that confidently ships something broken.
- Explicit conventions, written down, not tribal knowledge.
- Machine-checkable gates so the agent can verify its own work.
- Discoverable structure: an agent should find things the way you would.
Related terms
DX
DX, developer experience, is how good it feels for a human to work with a tool, library, or codebase: fast feedback, clear errors, sensible defaults, docs that answer the real question. It still matters in the agent era, and it tends to track how well agents work in the same codebase.
Read definition →AGENTS.md
AGENTS.md is a project file of standing instructions and conventions that an agent loads into context at the start of a session. It gives a repo its own durable memory, checked into version control next to the code.
Read definition →Skill
A skill is a packaged, reusable set of instructions an agent loads on demand for a specific kind of task. It is progressive disclosure of know-how instead of cramming everything into the system prompt.
Read definition →