Audit org health score integrity

What it's for

Makes Gitrevio's flagship Org Health Score defensible: leaders can see whether its 20-signal story is complete, comparable and robust before trusting the number.

What you give it

Every tool is a pure function: it computes from what you pass it and reads nothing on its own. Inputs split into evidence you supply from your connected systems, calibration your team owns, and numerical controls that affect precision but never the result's meaning.

{
  "as_of_ms": 1000,
  "component_definitions": [
    {
      "construct_id": "construct-0",
      "definition_version": "org-health-v1",
      "direction": "higher_better",
      "evidence_verified": true,
      "id": "component-0",
      "reference_center": 5,
      "reference_scale": 2,
      "source_id": "git",
      "weight": 0.25
    },
    {
      "construct_id": "construct-0",
      "definition_version": "org-health-v1",
      "direction": "higher_better",
      "evidence_verified": true,
      "id": "component-1",
      "reference_center": 5,
      "reference_scale": 2,
      "source_id": "git",
      "weight": 0.25
    },
    {
      "construct_id": "construct-1",
      "definition_version": "org-health-v1",
      "direction": "higher_better",
      "evidence_verified": true,
      "id": "component-2",
      "reference_center": 5,
      "reference_scale": 2,
      "source_id": "delivery",
      "weight": 0.25
    },
    {
      "construct_id": "construct-1",
      "definition_version": "org-health-v1",
      "direction": "lower_better",
      "evidence_verified": true,
      "id": "component-3",
      "reference_center": 5,
      "reference_scale": 2,

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.

{
  "decision": "publish_aggregate_org_health_score",
  "finding": "aggregate_org_health_pressure",
  "group_summaries": [
    {
      "group_id": "platform",
      "mean_score": 41.25,
      "p10_score": 35.75,
      "p90_score": 47.25,
      "scope_count": 5
    },
    {
      "group_id": "product",
      "mean_score": 42.5,
      "p10_score": 37.75,
      "p90_score": 49.75,
      "scope_count": 5
    }
  ],
  "integrity_diagnostics": {
    "missing_or_failed_invariance_certificate": 0,
    "missing_scope_component": 0,
    "suppressed_small_group": 0
  },
  "limitations": [
    "The composite is descriptive and is not a causal estimand or management target.",
    "Aggregate scores cannot rank people or authorize employment, compensation, or surveillance actions.",
    "A passed audit does not prove that the score predicts future business outcomes; validate that separately."
  ],
  "method": "point_in_time_composite_reconstruction_invariance_redundancy_and_leave_one_out_audit",
  "redundancy_pairs": [],
  "summary": {
    "aggregate_mean_score": 41.88,
    "complete_scope_count": 10,
    "component_count": 4,
    "construct_count": 2,
    "effective_component_count": 4,
    "expected_scope_count": 10,
    "maximum_leave_one_out_score_change": 10,
    "publishable_group_count": 2,
    "scope_coverage": 1,
    "suppressed_small_group_count": 0
  }
}

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 the score version, target period, evidence cutoff, component direction/weight/reference distribution, source snapshots, expected aggregate scopes and lawful consent before reconstructing any score.
2. 2 Require one complete version-consistent component vector per expected scope, reconcile every source snapshot, suppress small groups, and require current measurement-invariance certificates before comparisons across publishable groups.
3. 3 Calculate construct concentration, effective component count, cross-construct correlation and leave-one-component-out score sensitivity; publish only aggregate distributions when the complete measurement system passes.

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 20 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": "reconstruct the organizationhealth composite from frozen" }
  → finds "audit_org_health_score_integrity"

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

gitrevio_capability_run
  { "capability_id": "audit_org_health_score_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 People, retention & knowledge →