Audit decision flow integrity

What it's for

Makes invisible management queues measurable: leaders see where decisions remain open, loop, lose ownership, or accumulate tail delay before governance debt becomes delivery debt.

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.

{
  "bootstrap_draws": 300,
  "confidence_level": 0.8,
  "events": [
    {
      "decision_id": "product-decision-00",
      "dwell_hours": 10,
      "flow_id": "product-approval",
      "id": "product-approval-00-0",
      "owner_assigned": true,
      "owner_role": "product-owner",
      "sequence": 0,
      "state": "proposed",
      "terminal": false,
      "weight": 1
    },
    {
      "decision_id": "product-decision-00",
      "dwell_hours": 20,
      "flow_id": "product-approval",
      "id": "product-approval-00-1",
      "owner_assigned": true,
      "owner_role": "tech-lead",
      "sequence": 1,
      "state": "technical-review",
      "terminal": false,
      "weight": 1
    },
    {
      "decision_id": "product-decision-00",
      "dwell_hours": 5,
      "flow_id": "product-approval",
      "id": "product-approval-00-2",
      "owner_assigned": true,
      "owner_role": "product-owner",
      "sequence": 2,
      "state": "approved",
      "terminal": true,
      "weight": 1
    },
    {
      "decision_id": "product-decision-01",
      "dwell_hours": 10,
      "flow_id": "product-approval",

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.

{
  "configuration": {
    "bonferroni_one_sided_tail_probability": 0.05,
    "bootstrap_draws": 300,
    "confidence_level": 0.8,
    "maximum_cycle_fraction": 0.1,
    "maximum_lead_time_hours_p90": 720,
    "maximum_unowned_dwell_fraction": 0.05,
    "maximum_unresolved_fraction": 0.2,
    "minimum_decision_count": 20,
    "seed": 23,
    "simultaneous_gate_count": 4
  },
  "decision": "represented_decision_flows_clear_integrity_gates",
  "flow_diagnostics": [
    {
      "cycle_fraction": 0,
      "cycle_fraction_upper_bound": 0,
      "decision": "decision_flow_integrity_supported",
      "decision_count": 20,
      "failed_gates": [],
      "flow_id": "product-approval",
      "lead_time_hours_p90": 35,
      "lead_time_hours_p90_upper_bound": 35,
      "mean_handoff_count": 2,
      "state_bottlenecks": [
        {
          "event_count": 20,
          "mean_dwell_hours": 20,
          "p90_dwell_hours": 20,
          "state": "technical-review"
        },
        {
          "event_count": 20,
          "mean_dwell_hours": 10,
          "p90_dwell_hours": 10,
          "state": "proposed"
        },
        {
          "event_count": 20,
          "mean_dwell_hours": 5,
          "p90_dwell_hours": 5,
          "state": "approved"
        }

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 Reconstruct each decision from immutable ordered state events, preserving open decisions, dwell time, aggregate owner role, terminal semantics and one constant decision weight.
2. 2 Within each flow calculate weighted unresolved and cycle fractions, unowned dwell share, p90 elapsed lead time, handoffs and state dwell bottlenecks; resample whole decisions to retain their internal event dependence.
3. 3 Bonferroni-adjust the four one-sided gates across every screened flow and request remediation whenever conservative support, ownership, acyclicity or lead-time limits fail.

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 management decision histories for unresolved" }
  → finds "audit_decision_flow_integrity"

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

gitrevio_capability_run
  { "capability_id": "audit_decision_flow_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 →