Audit probabilistic forecasts

What it's for

Checks whether your team's confident predictions were actually accurate, calibrated and discriminating — and whether they beat simply quoting the base rate.

Makes every probabilistic ETA and risk claim accountable through proper scores, reliability curves, and uncertainty intervals.

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": 100,
  "forecasts": [
    {
      "id": "forecast-0",
      "outcome": false,
      "probability": 0.1
    },
    {
      "id": "forecast-1",
      "outcome": false,
      "probability": 0.2
    },
    {
      "id": "forecast-2",
      "outcome": false,
      "probability": 0.25
    },
    {
      "id": "forecast-3",
      "outcome": true,
      "probability": 0.3
    },
    {
      "id": "forecast-4",
      "outcome": false,
      "probability": 0.4
    },
    {
      "id": "forecast-5",
      "outcome": true,
      "probability": 0.55
    },
    {
      "id": "forecast-6",
      "outcome": true,
      "probability": 0.6
    },
    {
      "id": "forecast-7",
      "outcome": false,
      "probability": 0.7
    },
    {

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.

{
  "bootstrap_95_intervals": {
    "brier_score": {
      "high_95": 0.2361,
      "low_95": 0.0667
    },
    "brier_skill_score": {
      "high_95": 0.725,
      "low_95": -0.3558
    },
    "expected_calibration_error": {
      "high_95": 0.298,
      "low_95": 0.027
    }
  },
  "brier_decomposition": {
    "outcome_uncertainty": 0.25,
    "reliability_penalty": 0.009,
    "resolution_value": 0.1111
  },
  "calibration": {
    "bins": [
      {
        "bin": 1,
        "calibration_gap": 0.0667,
        "count": 6,
        "mean_forecast": 0.2333,
        "observed_rate": 0.1667,
        "weight": 6
      },
      {
        "bin": 2,
        "calibration_gap": -0.1167,
        "count": 6,
        "mean_forecast": 0.7167,
        "observed_rate": 0.8333,
        "weight": 6
      }
    ],
    "expected_calibration_error": 0.0917,
    "intercept": 0.2186,
    "maximum_calibration_error": 0.1167,
    "regression_converged": true,
    "slope": 1.5136

How it works

Forecasting & survival — Estimate when something completes or fails, with censoring and unresolved work handled honestly rather than dropped.

1. 1 Audit whether resolved probability forecasts are accurate, calibrated, discriminating, and better than a base-rate prediction.
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 whether resolved probability forecasts are" }
  → finds "audit_probabilistic_forecasts"

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

gitrevio_capability_run
  { "capability_id": "audit_probabilistic_forecasts", "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 Measurement integrity →