{
  "object_name": "Data Lineage Map",
  "object_slug": "data-lineage-map",
  "version": "1.0",
  "last_reviewed": "2026-06-24",
  "owner": "LPM / Lapemo",
  "object_type": "LPM Knowledge Object",
  "primary_lpm_layers": [
    "Information Ecology",
    "Platform Structure",
    "Governance Architecture",
    "AI Amplification"
  ],
  "connected_lpm_layers": [
    "Ownership Map",
    "Decision Architecture",
    "Communication Architecture",
    "Evidence Checklist",
    "Source-of-Truth Map"
  ],
  "purpose": "Trace how data moves from source to transformation, consumer, decision, workflow, AI model, agent, and control evidence.",
  "intended_audience": [
    "Executives",
    "Transformation Leaders",
    "Data Leaders",
    "Platform Owners",
    "AI Governance Teams",
    "Risk and Compliance",
    "Product and Operations Leaders"
  ],
  "required_fields": [
    {
      "name": "Lineage object ID",
      "definition": "Unique identifier for the data lineage object, domain, data product, metric, workflow, or AI use case",
      "required": "Yes"
    },
    {
      "name": "Business domain",
      "definition": "Customer, employee, product, finance, risk, sales, delivery, operations, platform, or AI",
      "required": "Yes"
    },
    {
      "name": "Business question / use case",
      "definition": "The decision, metric, process, report, AI use case, or control this data supports",
      "required": "Yes"
    },
    {
      "name": "Source system",
      "definition": "Original system where the data is created or mastered",
      "required": "Yes"
    },
    {
      "name": "Source object / table / document",
      "definition": "Specific table, API object, file, event, document, record, or data product",
      "required": "Yes"
    },
    {
      "name": "Source owner",
      "definition": "Business owner accountable for meaning, accuracy, and approved use",
      "required": "Yes"
    },
    {
      "name": "Technical owner",
      "definition": "System, data platform, integration, or engineering owner accountable for reliability",
      "required": "Yes"
    },
    {
      "name": "Data steward",
      "definition": "Role accountable for definition, metadata, quality checks, retention, and lifecycle hygiene",
      "required": "Required when material"
    },
    {
      "name": "Transformation steps",
      "definition": "Joins, calculations, enrichment, cleansing, aggregation, model features, or manual changes applied to the source",
      "required": "Yes"
    },
    {
      "name": "Transformation owner",
      "definition": "Role accountable for transformation logic and approval",
      "required": "Yes"
    },
    {
      "name": "Integration path",
      "definition": "API, ETL/ELT, event stream, file transfer, webhook, manual upload, RPA, or agentic workflow",
      "required": "Yes"
    },
    {
      "name": "Storage / processing layer",
      "definition": "Warehouse, lakehouse, operational store, BI model, vector index, feature store, cache, or knowledge base",
      "required": "Yes"
    },
    {
      "name": "Downstream consumers",
      "definition": "Dashboards, metrics, apps, teams, controls, workflows, models, agents, vendors, or customers that consume the data",
      "required": "Yes"
    },
    {
      "name": "Decision or action supported",
      "definition": "What the data helps decide, automate, approve, escalate, report, or govern",
      "required": "Yes"
    },
    {
      "name": "Data quality checks",
      "definition": "Completeness, accuracy, timeliness, validity, reconciliation, duplicate checks, or exception thresholds",
      "required": "Yes"
    },
    {
      "name": "Freshness window",
      "definition": "How current the data must be to remain decision-grade or AI-safe",
      "required": "Yes"
    },
    {
      "name": "Sensitivity / classification",
      "definition": "Internal, confidential, restricted, regulated, customer-sensitive, employee-sensitive, legal-sensitive, or public",
      "required": "Yes"
    },
    {
      "name": "Access rule",
      "definition": "Who can view, edit, export, query, embed, retrieve, summarize, or automate against the data",
      "required": "Yes"
    },
    {
      "name": "AI usage boundary",
      "definition": "Whether AI can retrieve, summarize, classify, recommend, transform, update, or act on the data",
      "required": "Yes"
    },
    {
      "name": "Human review rule",
      "definition": "When a human must validate the data, output, or action before it is used",
      "required": "Required when material"
    },
    {
      "name": "Evidence link",
      "definition": "Proof source for the lineage path, such as catalog link, data contract, pipeline run, dashboard definition, or control record",
      "required": "Yes"
    },
    {
      "name": "Known gaps / exceptions",
      "definition": "Manual steps, undocumented transforms, duplicate sources, stale fields, broken ownership, or ungoverned AI consumption",
      "required": "Yes"
    },
    {
      "name": "Confidence rating",
      "definition": "High, medium, low, provisional, stale, disputed, or retired",
      "required": "Yes"
    },
    {
      "name": "Review date",
      "definition": "Date the lineage path must be reviewed again",
      "required": "Yes"
    },
    {
      "name": "Version",
      "definition": "Object version, owner, last reviewed date, and change history",
      "required": "Yes"
    }
  ],
  "lineage_stages": [
    {
      "stage": "1. Create / master",
      "what_it_proves": "Where the data is first created or legally mastered",
      "examples": "CRM account, HRIS employee record, policy repository, Jira initiative",
      "owners": "Business owner, system owner, data steward",
      "common_risk": "Unclear master, duplicate records, missing owner"
    },
    {
      "stage": "2. Capture / ingest",
      "what_it_proves": "How the data enters the platform or workflow",
      "examples": "API, stream, ETL job, form, file upload, vendor feed",
      "owners": "Integration owner, platform owner",
      "common_risk": "Manual exports, hidden spreadsheets, undocumented feeds"
    },
    {
      "stage": "3. Transform / enrich",
      "what_it_proves": "How the data is changed, calculated, joined, modeled, or cleaned",
      "examples": "Metric formula, semantic model, feature engineering, data cleansing",
      "owners": "Data product owner, analytics owner, engineering owner",
      "common_risk": "Unapproved formulas, untested logic, stale joins"
    },
    {
      "stage": "4. Store / index",
      "what_it_proves": "Where transformed data is persisted or made searchable",
      "examples": "Warehouse, lakehouse, BI model, vector index, feature store",
      "owners": "Platform owner, data owner, security owner",
      "common_risk": "Uncontrolled copies, retention gaps, shadow indexes"
    },
    {
      "stage": "5. Consume / interpret",
      "what_it_proves": "Who uses the data and through what experience",
      "examples": "Dashboard, report, app screen, AI assistant, governance review",
      "owners": "Consumer owner, product owner, analyst owner",
      "common_risk": "Conflicting dashboards, no context, weak definitions"
    },
    {
      "stage": "6. Decide / act",
      "what_it_proves": "What decision, workflow, automation, or escalation depends on the data",
      "examples": "Prioritization, risk review, customer action, agent handoff, control approval",
      "owners": "Decision owner, process owner, control owner",
      "common_risk": "AI acts without review, stale data drives decision"
    },
    {
      "stage": "7. Evidence / audit",
      "what_it_proves": "How the organization proves the data path and decision were valid",
      "examples": "Data catalog, lineage graph, pipeline log, decision log, evidence checklist",
      "owners": "Governance owner, audit owner, source owner",
      "common_risk": "No proof, no replay, no confidence trail"
    }
  ],
  "lineage_object_types": [
    {
      "type": "Metric lineage",
      "lineage_path": "Source to formula to dashboard to executive decision",
      "examples": "Revenue, cycle time, AI ROI, risk score, adoption rate",
      "primary_owners": "Metric owner, data steward, analytics owner",
      "failure_mode": "Competing definitions and dashboard drift"
    },
    {
      "type": "Customer lineage",
      "lineage_path": "Customer master to engagement to action",
      "examples": "Account status, contract, support signal, renewal risk",
      "primary_owners": "Sales / success owner, CRM owner, data owner",
      "failure_mode": "AI outreach based on stale or wrong context"
    },
    {
      "type": "Employee lineage",
      "lineage_path": "HRIS to access, org design, capacity, and AI workforce planning",
      "examples": "Role, manager, team, skills, access, cost center",
      "primary_owners": "People owner, HRIS owner, identity owner",
      "failure_mode": "Bad routing, access errors, shadow org structure"
    },
    {
      "type": "Work lineage",
      "lineage_path": "Work intake to prioritization to delivery and outcome",
      "examples": "Initiatives, dependencies, blockers, delivery health, benefits",
      "primary_owners": "Product owner, PMO owner, work system owner",
      "failure_mode": "Hidden work and false delivery status"
    },
    {
      "type": "Governance lineage",
      "lineage_path": "Policy/control to exception to evidence and audit trail",
      "examples": "Risk, control, policy, approval, incident, exception",
      "primary_owners": "GRC owner, risk owner, control owner",
      "failure_mode": "Unreviewed exception or missing evidence"
    },
    {
      "type": "AI model / agent lineage",
      "lineage_path": "Training or retrieval data to prompt/model to output to human review",
      "examples": "Model features, RAG source, prompt, recommendation, automated action",
      "primary_owners": "AI owner, data owner, governance owner",
      "failure_mode": "AI output treated as fact without source trace"
    },
    {
      "type": "Knowledge lineage",
      "lineage_path": "Knowledge object to published artifact to AI retrieval and use",
      "examples": "SOP, playbook, framework object, policy, prompt library",
      "primary_owners": "Content owner, knowledge steward, AI retrieval owner",
      "failure_mode": "Stale documents becoming enterprise memory"
    }
  ],
  "company_versions": {
    "500_plus": [
      {
        "dimension": "Design intent",
        "recommended_pattern": "Create basic visibility before the company scales into duplicated tools, unowned dashboards, and AI pilots using weak data."
      },
      {
        "dimension": "Minimum lineage scope",
        "recommended_pattern": "Map the top 10 to 25 critical data paths: customer, employee, finance, delivery, product, risk, and active AI initiatives."
      },
      {
        "dimension": "Primary systems",
        "recommended_pattern": "CRM, HRIS, work system, finance system, knowledge base, BI tool, and AI pilot workspace."
      },
      {
        "dimension": "Operating pattern",
        "recommended_pattern": "Quarterly lineage review with business owners, data steward, technology owner, and executive sponsor."
      },
      {
        "dimension": "AI focus",
        "recommended_pattern": "AI can only summarize or recommend from named sources with human review for customer, employee, financial, risk, or external-facing use."
      },
      {
        "dimension": "Red flags",
        "recommended_pattern": "Spreadsheet exports, dashboard-only truth, founder-memory definitions, unowned AI prompts, and unclear data freshness."
      }
    ],
    "5000_plus": [
      {
        "dimension": "Design intent",
        "recommended_pattern": "Move from local data knowledge to domain-owned lineage that supports cross-functional decisions and scaled AI use cases."
      },
      {
        "dimension": "Minimum lineage scope",
        "recommended_pattern": "Map critical data products, enterprise metrics, system integrations, decision dashboards, governance controls, and AI model inputs."
      },
      {
        "dimension": "Primary systems",
        "recommended_pattern": "CRM, HRIS, ERP, work management, service desk, data warehouse/lakehouse, BI semantic layer, GRC, IAM, AI platform."
      },
      {
        "dimension": "Operating pattern",
        "recommended_pattern": "Domain lineage owners, data product reviews, data catalog entries, quality thresholds, and formal exception paths."
      },
      {
        "dimension": "AI focus",
        "recommended_pattern": "RAG sources, model features, agent workflows, and AI outputs must reference governed sources, data contracts, and review rules."
      },
      {
        "dimension": "Red flags",
        "recommended_pattern": "Multiple dashboards for the same metric, undocumented transformations, BI logic outside catalog, and model/agent consumption without lineage."
      }
    ],
    "10000_plus": [
      {
        "dimension": "Design intent",
        "recommended_pattern": "Create enterprise-grade lineage as a control layer for decisions, risk, AI, audit, regulation, and operating-model resilience."
      },
      {
        "dimension": "Minimum lineage scope",
        "recommended_pattern": "Map all Tier 1 and Tier 2 data domains, regulatory/control data paths, AI-critical datasets, executive metrics, and external reporting feeds."
      },
      {
        "dimension": "Primary systems",
        "recommended_pattern": "Enterprise data catalog, MDM, data lakehouse, semantic layer, API gateway, event platform, GRC, IAM, model registry, agent orchestration, observability."
      },
      {
        "dimension": "Operating pattern",
        "recommended_pattern": "Automated lineage capture, lineage control board, domain data councils, evidence packs, policy-as-code checks, and supersession management."
      },
      {
        "dimension": "AI focus",
        "recommended_pattern": "AI models and agents require retrieval lineage, feature lineage, prompt/output logging, human review policy, model risk tier, and audit replay."
      },
      {
        "dimension": "Red flags",
        "recommended_pattern": "Federated business units creating conflicting truth, unmanaged data sharing, vendor feeds without ownership, and AI agents acting on low-confidence data."
      }
    ]
  },
  "scoring_logic": [
    {
      "dimension": "Ownership clarity",
      "score_range": "0-5",
      "good_state": "Every source, transformation, consumer, and decision path has a named owner."
    },
    {
      "dimension": "Source clarity",
      "score_range": "0-5",
      "good_state": "The authoritative source and upstream origin are clearly defined."
    },
    {
      "dimension": "Transformation transparency",
      "score_range": "0-5",
      "good_state": "Calculation, enrichment, joins, model features, and manual steps are documented and owned."
    },
    {
      "dimension": "Consumer visibility",
      "score_range": "0-5",
      "good_state": "Dashboards, decisions, workflows, controls, AI models, and agents using the data are known."
    },
    {
      "dimension": "Evidence strength",
      "score_range": "0-5",
      "good_state": "Lineage is supported by catalog links, pipeline logs, definitions, data contracts, and review history."
    },
    {
      "dimension": "Freshness discipline",
      "score_range": "0-5",
      "good_state": "Refresh cadence and stale-data triggers are defined and monitored."
    },
    {
      "dimension": "AI safety boundary",
      "score_range": "0-5",
      "good_state": "AI retrieval, recommendation, update, and action boundaries are explicit and reviewable."
    },
    {
      "dimension": "Exception management",
      "score_range": "0-5",
      "good_state": "Manual steps, duplicates, shadow sources, broken feeds, and disputed lineage have clear escalation paths."
    }
  ],
  "readiness_formula": "Average the eight dimension scores. 0-1.9 Fragile, 2.0-3.4 Developing, 3.5-4.4 Governed, 4.5-5.0 AI-ready.",
  "ai_prompts": [
    "Given this data object, identify the source system, transformation steps, downstream consumers, decision dependencies, and missing owners.",
    "Compare the declared source of truth against actual downstream dashboards, workflows, AI tools, and manual exports. Flag duplicate or conflicting lineage paths.",
    "Score this lineage path from 0 to 5 across ownership clarity, source clarity, transformation transparency, consumer visibility, evidence strength, freshness discipline, AI safety, and exception management.",
    "Identify whether this dataset is safe for AI retrieval, summary, recommendation, classification, or autonomous action. Explain the human review rule needed.",
    "Generate a lineage exception report showing stale data, undocumented transformations, shadow copies, missing owners, weak evidence, and high-risk AI consumers.",
    "Create a migration plan to move this lineage path from manual documentation to governed Lapemo ingestion."
  ],
  "validation_rules": [
    "Every lineage object must have one accountable source owner and one technical owner.",
    "Every transformation must have a documented owner, purpose, and approval state.",
    "Every downstream AI use must reference an approved source, freshness window, sensitivity rule, and human review boundary.",
    "Every decision-grade metric must have a named source, formula, steward, quality threshold, and review date.",
    "No dashboard, model, agent, workflow, or external report should consume data from an unowned or disputed lineage path.",
    "Manual exports, spreadsheet changes, and shadow copies must be flagged as exceptions unless explicitly approved.",
    "If data is stale, disputed, low-confidence, or missing evidence, it cannot be used as authoritative truth without owner approval.",
    "Status must never be encoded only by color; use labels such as approved, provisional, stale, disputed, retired, or exception."
  ],
  "lapemo_mapping": [
    {
      "lapemo_object": "Knowledge object",
      "fields_or_entities": "Data Lineage Map",
      "use": "Canonical reusable artifact for lineage readiness and AI-safe data consumption."
    },
    {
      "lapemo_object": "Ownership object",
      "fields_or_entities": "Source owner, technical owner, steward, transformation owner",
      "use": "Connects lineage to accountability."
    },
    {
      "lapemo_object": "Information object",
      "fields_or_entities": "Source, transformation, storage, consumer, evidence",
      "use": "Connects lineage to enterprise knowledge and data products."
    },
    {
      "lapemo_object": "Platform object",
      "fields_or_entities": "Systems, integrations, APIs, pipelines, BI, model registry, vector index",
      "use": "Connects lineage to enterprise systems under control."
    },
    {
      "lapemo_object": "Decision object",
      "fields_or_entities": "Decision/action supported, evidence link, confidence",
      "use": "Connects data to decisions and outcomes."
    },
    {
      "lapemo_object": "Governance object",
      "fields_or_entities": "Sensitivity, access, control, exception, review date",
      "use": "Connects lineage to risk, compliance, and auditability."
    },
    {
      "lapemo_object": "AI object",
      "fields_or_entities": "AI usage boundary, human review rule, output log, agent consumer",
      "use": "Connects data lineage to AI governance and control."
    }
  ],
  "render_targets": [
    "DOCX template",
    "PDF guide",
    "Website Markdown",
    "JSON skill schema",
    "Interactive form",
    "Lapemo onboarding workflow",
    "Data lineage graph",
    "AI readiness assessment"
  ],
  "automation_policy": {
    "auto_update": false,
    "recommended_mode": "Flag stale lineage, missing ownership, undocumented transformation, broken evidence, high-risk AI consumer, and duplicate truth paths for human approval.",
    "human_approval_required_for": [
      "source owner changes",
      "AI usage boundary changes",
      "sensitivity changes",
      "decision-grade status",
      "retiring or superseding a source",
      "regulatory/control lineage"
    ]
  }
}