Card snapshot

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "name": "Eval Engine API",
  "description": "Pay-per-call AI evaluation engine. Score LLM outputs, agent trajectories, and model responses against benchmark rubrics using Workers AI.",
  "url": "https://eval.zuluworksai.com",
  "version": "0.1.0",
  "skills": [
    {
      "id": "evaluate",
      "name": "Evaluate Output",
      "description": "Score an LLM output against a benchmark rubric. Returns 0-1 score with reasoning.",
      "paymentRequired": true
    },
    {
      "id": "list_benchmarks",
      "name": "List Benchmarks",
      "description": "List all available evaluation benchmarks.",
      "paymentRequired": false
    },
    {
      "id": "get_benchmark",
      "name": "Get Benchmark",
      "description": "Get detailed information about a specific benchmark.",
      "paymentRequired": false
    }
  ],
  "supportedInterfaces": [
    {
      "type": "a2a",
      "url": "https://eval.zuluworksai.com/.well-known/agent-card.json"
    },
    {
      "type": "mcp",
      "url": "https://eval.zuluworksai.com/mcp"
    }
  ],
  "capabilities": {
    "payment": {
      "protocol": "x402",
      "network": "eip155:8453",
      "asset": "USDC",
      "price": "0.005"
    }
  },
  "owner": {
    "name": "ZuluWorksAI",
    "url": "https://zuluworksai.com"
  }
}