关于这个工具
AXIS 是一个开源工具和评分框架,旨在衡量服务对 AI 智能体的友好程度。它通过运行真实场景,生成 0–100 的综合评分,帮助开发者识别并修复影响智能体效率的瓶颈。
核心功能
- 场景运行:支持运行真实智能体场景,评估服务在实际交互中的表现。
- 四维评分:从目标达成、环境、服务和智能体四个维度进行评分,每个维度提供详细分解。
- 项目初始化:通过
axis init命令快速初始化项目,交互式配置场景目录和智能体。 - 技能安装:自动运行
npx skills add netlify/axis --all,将 configure-axis 技能安装到检测到的智能体配置目录。 - API 密钥支持:需要至少一个受支持智能体的 API 密钥(例如 Claude Code 的 ANTHROPIC_API_KEY)。
使用流程
- 在项目根目录运行
axis init,根据提示配置场景目录和智能体。 2. 生成两个文件:axis.json示例场景和智能体配置文件。 3. 运行场景,获取 0–100 的 AXIS 综合评分。 4. 根据四维评分结果,定位并修复影响智能体体验的问题。
评分维度
- 目标达成:智能体是否完成任务?根据您的评分标准检查。
- 环境:智能体与系统环境的交互情况。
- 服务:服务对智能体请求的响应质量。
- 智能体:智能体自身的执行表现。 AXIS 采用免费模式,适合 AI 智能体开发者、服务提供商和平台工程师使用。
功能与使用场景
{json|js|ts} -minimal config with your chosen scenarios path and agentsAfter the files are written, init also runs npx skills add netlify/axis --all to install the configure-axis skill into your detected agent config directoriesAn API key for at least one supported agent (for example, ANTHROPIC_API_KEY for Claude Code)Breakdowns for each of the four scoring dimensions: Goal Achievement, Environment, Service, and AgentDimension What It Tells You Goal Achievement Did the agent complete the task? Scored against your rubric checksExecution & Agents -how AXIS runs scenarios, supported and custom agents, and workspace isolationExecution & Agents -how AXIS runs scenarios, supported and custom agents, and workspace isolation.Initialize Your Project From your project root, run: axis init In an interactive terminal, this prompts you for the scenarios directory, which agents to include (comma-separated, eInterpret Your Results The AXIS Result is a composite of four dimensions, each measuring a different aspect of the agent's interaction with your systemIt then creates two files: axisjson -a sample scenario that asks the agent to create a file with specific contentNext Steps Scoring Framework -how the four dimensions are calculated, what signals drive each score, and why the scoring works the way it does
