Audit organizational change simulation integrity

What it's for

Makes the private-beta What-If Simulator's local-data, Monte Carlo and second-order-effect claims auditable before leaders rely on a scenario.

What you give it

Inputs split into evidence read from your connected systems, calibration your team owns, and numerical controls that affect precision but never the result's meaning.

{
  "as_of_ms": 19008000000,
  "dependency_edges": [
    {
      "case_id": "departure-case",
      "downstream_factor_id": "review",
      "evidence_verified": true,
      "id": "capacity-to-review",
      "lag_periods": 1,
      "observed_through_ms": 15984000000,
      "source_artifact_id": "change-evidence",
      "transmission_weight": 0.5,
      "upstream_factor_id": "capacity"
    },
    {
      "case_id": "departure-case",
      "downstream_factor_id": "quality",
      "evidence_verified": true,
      "id": "review-to-quality",
      "lag_periods": 1,
      "observed_through_ms": 15984000000,
      "source_artifact_id": "change-evidence",
      "transmission_weight": 0.4,
      "upstream_factor_id": "review"
    }
  ],
  "evidence_artifacts": [
    {
      "id": "change-evidence",
      "immutable_hash": "artifact-hash",
      "independently_verified": true,
      "observed_at_ms": 15984000000,
      "scope_id": "organization",
      "source_system_id": "point-in-time-projection"
    }
  ],
  "factor_assumptions": [
    {
      "case_id": "departure-case",
      "effect_stage_id": "direct",
      "effective_sample_size": 20,
      "estimate": 0.8,
      "evidence_verified": true,
      "factor_family_id": "capacity",

What you get back

This is the actual output of running the example above — computed by the same function the platform calls, not an illustration.

{
  "case_diagnostics": [
    {
      "case_id": "departure-case",
      "change_type_id": "departure",
      "dependency_edge_count": 2,
      "factor_count": 4,
      "failed_gates": [],
      "passed": true,
      "subject_reference_kind": "opaque_subject"
    }
  ],
  "configuration": {
    "as_of_ms": 19008000000,
    "minimum_effective_support": 10,
    "minimum_history_days": 90,
    "minimum_verified_case_fraction": 0.95
  },
  "decision": "pass",
  "failed_gates": {
    "case_failure_counts": {},
    "orphan_dependency_edge_ids": [],
    "orphan_factor_assumption_ids": []
  },
  "guardrails": [
    "Passing verifies submitted lineage, temporal integrity, support and safeguards; it does not prove a causal effect or that every second-order dependency was observed.",
    "Opaque subject scenarios may support continuity planning only; protected traits, inferred intent, covert surveillance and automated employment decisions are outside this contract.",
    "Passing never authorizes hiring, firing, reassignment, monitoring, access changes, procurement, rollout or migration."
  ],
  "method": "point_in_time_organizational_change_simulation_integrity_audit_v1",
  "summary": {
    "case_count": 1,
    "dependency_edge_count": 2,
    "factor_assumption_count": 4,
    "model_version_count": 1,
    "verified_case_count": 1,
    "verified_case_fraction": 1
  }
}

How it works

Statistical audit & measurement — Check whether a number is fit to decide on: coverage, timing, reconciliation, and the gaps a dashboard hides.

1. 1 Freeze each scenario case, unchanged comparator, model version, baseline snapshot, decision time, financial basis and required factor families at the submitted as-of cutoff.
2. 2 Verify that the effective independently reviewed model was trained only on earlier evidence, permits the change type, passed calibration, excludes prohibited attributes and has enough local history and scenario draws.
3. 3 Trace every direct, second-order and recovery assumption to independently verified artifacts, enforce effective-sample-size and temporal gates, validate the factor DAG and require lawful-purpose, human-review, correction and access safeguards for opaque-subject scenarios.

Before you trust it

Every tool in the catalog ships with the conditions under which its answer is meaningful — and the conditions under which it should abstain instead of guessing.

Calibrating it to your org

Calibration workflow

1. 1 Define the management decision, target outcome, aggregate unit, privacy boundary, cadence, and prediction/intervention horizon for this organization.
2. 2 Build a tenant-scoped historical cohort using only information available before each prediction or decision; preserve zero periods, censoring, assignment probabilities, and unresolved outcomes when the method requires them.
3. 3 Estimate statistical parameters on training history, but obtain costs, utilities, risk tolerance, practical-effect thresholds, capacity, and policy constraints from accountable decision owners.
4. 4 Validate on later time windows or held-out aggregate units at the deployment grain, against a simple baseline and the function-specific validation strategy.
5. 5 Deploy only if the returned decision clears evidence, overlap, calibration, robustness, and guardrail checks; warning, unsupported, schema-gap, and fallback decisions are abstentions.
6. 6 Monitor realized outcomes, data drift, coverage, and decision regret; recalibrate at a governed cadence or after a detected regime/definition change, never merely because a stakeholder dislikes the result.

Call it from your AI

You don't wire up 388 tools in your MCP client. The GitRevio MCP server exposes 18 tools, three of which let an agent search the catalog, read a tool's schema, and run it — so the assistant finds this one on its own.

gitrevio_capabilities_search
  { "q": "audit whether an organizational or technology" }
  → finds "audit_organizational_change_simulation_integrity"

gitrevio_capability_describe
  { "capability_id": "audit_organizational_change_simulation_integrity" }
  → returns the input schema and agent guidance shown on this page

gitrevio_capability_run
  { "capability_id": "audit_organizational_change_simulation_integrity", "arguments": { ... } }
  → returns the result shown above

Works in Claude Desktop, Claude Code, Cursor, Cline, Continue.dev, Goose and Aider. See the MCP server.

Related tools

See every tool in Org design, incentives & decisions →