{
  "id": "skill-area:ai-evaluation",
  "_kind": "SkillArea",
  "_file": "domain/skill-areas/skill-areas-ecosystem-expansion.yaml",
  "_cluster": "domain",
  "attributes": {
    "displayName": "AI Evaluation",
    "description": "Systematic evaluation of AI model outputs — benchmark design, human\npreference collection, automated scoring pipelines, and red-teaming\nfor quality, safety, and alignment assessment.\n",
    "domains": [
      "domain:ml-ops"
    ],
    "expertiseLevels": [
      "intermediate",
      "expert"
    ]
  },
  "outgoingEdges": [
    {
      "from": "skill-area:ai-evaluation",
      "to": "domain:ml-ops",
      "kind": "applies_to",
      "attributes": {
        "confidence": "primary"
      }
    }
  ],
  "incomingEdges": [
    {
      "from": "skill-area:ai-agent-development",
      "to": "skill-area:ai-evaluation",
      "kind": "prerequisite_for_learning",
      "attributes": {
        "strength": "recommended"
      }
    },
    {
      "from": "stack-profile:prompt-engineering-workbench",
      "to": "skill-area:ai-evaluation",
      "kind": "requires_skill_area"
    },
    {
      "from": "tool:skillachi",
      "to": "skill-area:ai-evaluation",
      "kind": "tool_used_by",
      "attributes": {}
    },
    {
      "from": "tool:jupyter",
      "to": "skill-area:ai-evaluation",
      "kind": "used_for"
    },
    {
      "from": "tool:vllm",
      "to": "skill-area:ai-evaluation",
      "kind": "used_for"
    },
    {
      "from": "tool:tensorrt",
      "to": "skill-area:ai-evaluation",
      "kind": "used_for"
    },
    {
      "from": "tool:triton-inference",
      "to": "skill-area:ai-evaluation",
      "kind": "used_for"
    },
    {
      "from": "tool:onnx-runtime",
      "to": "skill-area:ai-evaluation",
      "kind": "used_for"
    },
    {
      "from": "tool:langsmith",
      "to": "skill-area:ai-evaluation",
      "kind": "tool_used_by",
      "attributes": {}
    },
    {
      "from": "tool:langfuse",
      "to": "skill-area:ai-evaluation",
      "kind": "tool_used_by",
      "attributes": {}
    },
    {
      "from": "tool:ragas",
      "to": "skill-area:ai-evaluation",
      "kind": "tool_used_by",
      "attributes": {}
    },
    {
      "from": "tool:ragas",
      "to": "skill-area:ai-evaluation",
      "kind": "used_for"
    }
  ]
}