AI agents don't just call models. They call your API. They authenticate, hit errors, parse responses, and decide whether to keep going.
Most services were never built for that.
Today, we're launching AXIS: an open source way to measure how well your service works with AI agents.
ALT Screenshot of the AXIS Report dashboard displayed on a white panel against a dark teal background. The header features the AXIS logo, the word “Report,” and a large green digital-style score of 84. Below is a table comparing AI agent performance across scenarios, with columns for Axis score, goal achievement, environment, service, agent rating, token usage, duration, and cost. Colored score badges in green, yellow, and red indicate performance metrics for different Claude Code configurations. The visible section includes scenarios such as “Agent Runners: Check run status” and “Agent Runners: Delegate second opinion,” presenting benchmarking data for AI coding agents.