Forecast org health operating loss

What it's for

Turns Org Health from a colored dashboard number into an accountable executive forecast: did it predict later outcomes here, and what operating loss and tail risk follow now?

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": 1000,
  "current_scopes": [
    {
      "evidence_verified": true,
      "group_id": "product",
      "id": "org-health-current-0",
      "observed_at_ms": 600,
      "org_health_score": 45,
      "previous_org_health_score": 43,
      "scope_id": "current-scope-0",
      "scope_size": 15
    },
    {
      "evidence_verified": true,
      "group_id": "product",
      "id": "org-health-current-1",
      "observed_at_ms": 600,
      "org_health_score": 53,
      "previous_org_health_score": 51,
      "scope_id": "current-scope-1",
      "scope_size": 16
    },
    {
      "evidence_verified": true,
      "group_id": "platform",
      "id": "org-health-current-2",
      "observed_at_ms": 600,
      "org_health_score": 61,
      "previous_org_health_score": 59,
      "scope_id": "current-scope-2",
      "scope_size": 17
    },
    {
      "evidence_verified": true,
      "group_id": "platform",
      "id": "org-health-current-3",
      "observed_at_ms": 600,
      "org_health_score": 69,
      "previous_org_health_score": 67,
      "scope_id": "current-scope-3",
      "scope_size": 18
    }
  ],

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.

{
  "current_scope_forecasts": [
    {
      "expected_loss_by_outcome": {
        "capacity_loss": 293.58,
        "delivery_loss": 748.22,
        "reliability_loss": 468.12
      },
      "group_id": "product",
      "scope_ref": "current-scope-0"
    },
    {
      "expected_loss_by_outcome": {
        "capacity_loss": 250,
        "delivery_loss": 635.67,
        "reliability_loss": 394.95
      },
      "group_id": "product",
      "scope_ref": "current-scope-1"
    },
    {
      "expected_loss_by_outcome": {
        "capacity_loss": 208.21,
        "delivery_loss": 528.96,
        "reliability_loss": 329.8
      },
      "group_id": "platform",
      "scope_ref": "current-scope-2"
    },
    {
      "expected_loss_by_outcome": {
        "capacity_loss": 175.74,
        "delivery_loss": 446.28,
        "reliability_loss": 277.94
      },
      "group_id": "platform",
      "scope_ref": "current-scope-3"
    }
  ],
  "decision": "forecast_available",
  "finding": "org_health_operating_loss_within_limit",
  "limitations": [
    "The company-local score is a predictive covariate, not a causal treatment or performance target.",
    "Loss definitions, perimeter, currency, horizon, and shared scenarios must be finance-owned and versioned.",

How it works

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

1. 1 Build strictly pre-outcome score, change, size and group features with finance-reconciled next-period delivery, reliability and capacity loss; hold out the newest whole period before fitting.
2. 2 Fit a ridge-regularized multivariate log-loss model with shrunk group effects and residual dependence, then require lower multivariate log score, enough outcome-level MAE wins, interval coverage, evidence verification and current-group support versus a global baseline.
3. 3 Only after validation, simulate company-local correlated outcome losses under one coherent common economic scenario per draw, add shared loss once, and report aggregate expected loss, VaR and CVaR with bounded opaque-scope detail.

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": "prove whether the companylocal organizationhealth score" }
  → finds "forecast_org_health_operating_loss"

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

gitrevio_capability_run
  { "capability_id": "forecast_org_health_operating_loss", "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 →