Stop guessing if agents
can use your service
Think Lighthouse, but for agent experience. AXIS — the Agent Experience Index Score — is open source tooling and a scoring framework to measure how well your APIs, services, and project structure work for AI agents.
$ npm i -g @netlify/axis $ axis init $ axis run 
Claude Code
Codex
Gemini
Kiro
Goose
opencode
fast-agent
OpenHands
Qwen Code
Kimi
Mistral Vibe
Blackbox
Stakpak
Poolside
Cursor
Auggie
Factory Droid
Qoder
Cline
Kilo
CopilotFour dimensions, one score.
A single pass/fail tells you nothing about why an agent struggled. AXIS scores four independent dimensions so you can focus on what matters: a slow API, a confusing layout, a noisy tool, or the agent's own decisions.
Did the agent actually finish the task? Scored against your rubric checks by an LLM judge.
Shell, filesystem, build tools. Measure whether your project structure and dev workflow trip agents up.
APIs, MCP tools, third-party services. Tells you whether your endpoints are actually usable by an agent.
Planning, tool selection, self-organization. Captures the quality of the agent's own decisions.
Score it. Baseline it. Gate CI on it.
AXIS is built to slot into the same place as your unit tests, just for agent experience. Run it locally to iterate, then turn on baselines and let your CI catch regressions automatically.
A JSON file with a prompt, a rubric, and optional setup steps. A minimal scenario is five lines.
23 built-in agents including Claude Code, Codex, Gemini, Cursor, Copilot, and more. Not listed? Register any agent via the custom agent API.
Snapshot a passing run, commit the baseline, and any future regression beyond noise tolerance fails the build.
Built with teams already building for agents.
AXIS was created by Netlify and is being developed in the open. These are the founding contributors — the first teams to run it, publish their results, and help shape the standard.
Ship for humans and
the agents they use
AXIS is open source and free.
You can wire it into your project in just a few minutes.