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, documentation that answers the actual question: all the things that make a developer productive instead of fighting friction. Good DX is why some tools spread by word of mouth and others get quietly abandoned.
Does it still matter with agents?
More than people expect. It is tempting to think that once an agent writes most of the code, human comfort stops mattering. But you still read the diffs, debug the failures, and decide what ships. A codebase with clean structure, fast tests, and readable errors is easier for you to review and reason about, and easier for the agent working inside it too.
The two are also correlated. The things that make a codebase pleasant for humans tend to make it legible for agents.
- Fast, honest feedback loops: quick builds, clear test output.
- Low surprise: consistent conventions, good defaults, obvious naming.
- Real documentation, kept close to the code it describes.
Related terms
AX
AX, agent experience, is how well a codebase or tool is set up for AI agents to work inside it: clear structure, written-down conventions, an AGENTS.md, and automated checks the agent can verify against. It is the emerging sibling of developer experience.
Read definition →Agent
An agent is a language model wrapped in a loop that lets it call tools, read the results, and decide what to do next. The model supplies the judgement; the loop and the tools give it hands.
Read definition →Harness
The harness is the code wrapped around a model that builds requests, runs tools, manages context, and enforces permissions. It is the agent minus the model, and it is where most of the real engineering lives.
Read definition →