Audit cluster randomization integrity

What it's for

Gives agents and leaders a pre-analysis integrity gate before a randomized team rollout is described as credible evidence.

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.

{
  "clusters": [
    {
      "assigned_arm": 0,
      "baseline_metrics": {
        "cycle_time": 0,
        "failure_rate": 0,
        "throughput": 0
      },
      "cluster_size": 8,
      "id": "experiment-cluster-0",
      "outcome_observed": false
    },
    {
      "assigned_arm": 1,
      "baseline_metrics": {
        "cycle_time": 1.85,
        "failure_rate": 0.17525773195876287,
        "throughput": 2.9
      },
      "cluster_size": 9,
      "id": "experiment-cluster-1",
      "outcome_observed": true
    },
    {
      "assigned_arm": 0,
      "baseline_metrics": {
        "cycle_time": 3.7,
        "failure_rate": 0.35051546391752575,
        "throughput": 5.8
      },
      "cluster_size": 10,
      "id": "experiment-cluster-2",
      "outcome_observed": true
    },
    {
      "assigned_arm": 1,
      "baseline_metrics": {
        "cycle_time": 0.5,
        "failure_rate": 0.5257731958762887,
        "throughput": 8.7
      },
      "cluster_size": 11,
      "id": "experiment-cluster-3",

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.

{
  "assumptions": [
    "Assignment was generated at cluster grain before outcomes, and baseline metrics were frozen before assignment was revealed.",
    "Practical standardized-difference and observation-rate limits are governed tolerances; randomization p-values are diagnostics, not substitutes for those limits.",
    "Cluster-size weighting targets the represented population; an equal-cluster estimand requires equal weights instead.",
    "Passing balance and observation checks does not rule out interference, noncompliance, outcome-definition changes, or post-randomization exclusions."
  ],
  "baseline_balance": {
    "mahalanobis_distance": 0.0297,
    "maximum_absolute_standardized_difference": 0.1336,
    "maximum_allowed": 0.5,
    "practical_balance_supported": true,
    "randomization_p_value_mahalanobis": 0.950249,
    "randomization_p_value_max_imbalance": 0.955224
  },
  "decision": "cluster_randomization_integrity_supported",
  "detail": {
    "returned_rows": 3,
    "total_rows": 3,
    "truncated": false
  },
  "method": "cluster_randomization_balance_attrition_permutation_audit_v1",
  "metrics": [
    {
      "absolute_standardized_difference": 0.1336,
      "metric": "cycle_time",
      "standardized_difference": -0.1336,
      "within_limit": true
    },
    {
      "absolute_standardized_difference": 0.1077,
      "metric": "throughput",
      "standardized_difference": 0.1077,
      "within_limit": true
    },
    {
      "absolute_standardized_difference": 0.0355,
      "metric": "failure_rate",
      "standardized_difference": 0.0355,
      "within_limit": true
    }
  ],
  "outcome_observation": {
    "control_rate": 0.96,

How it works

Causal inference & experiment design — Separate what a change caused from what merely moved alongside it.

1. 1 Audit cluster-randomized experiments for practical baseline imbalance and differential outcome observation, with cluster-size-weighted standardized differences and assignment permutation diagnostics.
2. 2 Evaluate the method-specific diagnostics and gates returned by the function, then abstain unless the declared decision clears them under locally governed thresholds.

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 clusterrandomized experiments for practical baseline" }
  → finds "audit_cluster_randomization_integrity"

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

gitrevio_capability_run
  { "capability_id": "audit_cluster_randomization_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 Causal evidence & experiments →