{
  "id": "workflow:synthetic-data-generation-pipeline",
  "_kind": "Workflow",
  "_file": "workflows/workflows/workflows-ai-era.yaml",
  "_cluster": "workflows",
  "attributes": {
    "displayName": "Synthetic Data Generation Pipeline",
    "workflowKind": "development",
    "triggerType": "on-demand",
    "typicalCadence": "per-milestone",
    "complexity": "cross-team",
    "description": "Designs and executes pipelines that produce synthetic training, evaluation,\nor test datasets — defining schema constraints and statistical\ndistributions, configuring generative models or rule-based generators,\nvalidating that synthetic outputs match real-data characteristics without\nleaking PII, running bias and fairness audits, and versioning artifacts in\na data registry. Produces validated synthetic datasets and a data-card.\nExcludes model training itself.\n"
  },
  "outgoingEdges": [
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "role:data-scientist",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "role:ml-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "role:data-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "skill-area:python-implementation",
      "kind": "requires_skill_area",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "skill-area:data-quality",
      "kind": "requires_skill_area",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "domain:data-science",
      "kind": "applies_to_domain",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "domain:ml-ops",
      "kind": "applies_to_domain",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "responsibility:data-quality-monitoring",
      "kind": "triggers_responsibility",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "responsibility:ai-safety-guardrails",
      "kind": "triggers_responsibility",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "org-unit:ml-platform-team",
      "kind": "performed_by_org_unit",
      "attributes": {}
    },
    {
      "from": "workflow:synthetic-data-generation-pipeline",
      "to": "org-unit:data-platform-team",
      "kind": "performed_by_org_unit",
      "attributes": {}
    }
  ],
  "incomingEdges": [
    {
      "from": "stack-profile:synthetic-data-generation",
      "to": "workflow:synthetic-data-generation-pipeline",
      "kind": "follows_workflow"
    }
  ]
}