跳到主要内容

AI:编排

AI 编排将三者串联:引擎在用户状态中检测时机、选定群组并选择行动,于是无需手动逐步接线,闭环即可运行。

At a glance

GraphQL
ai query: summarise, explain, suggest
MCP
Every prodantix.* tool, callable by an agent
MCP host
https://eu.mcp.prodantix.com
Auth
Access token
  • 在实时状态中检测关键时刻
  • 选择合适的群组和合适的行动
  • 闭合循环:行动成为引擎从中学习的下一个事件

工作原理

Every answer is grounded in rows the caller could already read. Citations are resolved server-side from a built candidate list rather than taken from the model’s reply, so an answer can only point at something that exists and the caller is entitled to see.

如何访问

SurfaceOperation
GraphQLai query: summarise, explain, suggest
MCPevery prodantix.* tool, callable by an agent

示例

GraphQL
query Explain($projectId: String!) {
  ai {
    explainMetric(
      projectId: $projectId
      metric: "order.completed"
      window: "P7D"
    ) {
      summary
      citations { kind id }
    }
  }
}

Pointing an agent at prodantix

The MCP surface exposes the same capabilities to an autonomous agent. See MCP for the tool list and protocol details.

JSON
{
  "mcpServers": {
    "prodantix": {
      "url": "https://eu.mcp.prodantix.com/mcp",
      "headers": { "Authorization": "Bearer <access token>" }
    }
  }
}