Forecast aggregate workforce capacity risk

What it's for

Gives executives and investors a forward capacity-risk view by role and cause, with uncertainty and data-support disclosure, while avoiding speculative individual attrition scoring.

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.

{
  "current_role_portfolio": [
    {
      "active_positions": 8,
      "capacity_per_position": 1,
      "required_capacity": 6,
      "role_id": "platform"
    },
    {
      "active_positions": 12,
      "capacity_per_position": 1,
      "required_capacity": 9,
      "role_id": "product"
    }
  ],
  "event_types": [
    "voluntary_exit"
  ],
  "historical_spells": [
    {
      "duration_days": 30,
      "event_type": "voluntary_exit",
      "id": "workforce-spell-0",
      "role_id": "product"
    },
    {
      "duration_days": 60,
      "event_type": "censored",
      "id": "workforce-spell-1",
      "role_id": "platform"
    },
    {
      "duration_days": 90,
      "event_type": "censored",
      "id": "workforce-spell-2",
      "role_id": "product"
    },
    {
      "duration_days": 120,
      "event_type": "censored",
      "id": "workforce-spell-3",
      "role_id": "platform"
    },
    {

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": [
    "Historical spells use stable role definitions, censoring is non-informative conditional on role and observed duration, and the future hazard regime is comparable.",
    "Role-period hazards are partially pooled toward the organization and current positions are exchangeable within role for aggregate planning.",
    "The no-replacement forecast is a capacity stress baseline; hiring, transfers, retention interventions, leave returns, and ramp dynamics should be layered as explicit scenarios."
  ],
  "configuration": {
    "event_types": [
      "voluntary_exit"
    ],
    "horizon_periods": 6,
    "maximum_shortfall_probability": 0.2,
    "period_days": 30,
    "role_prior_strength": 20,
    "simulations": 500
  },
  "decision": "aggregate_workforce_capacity_risk",
  "executive_summary": {
    "highest_risk_role": "product",
    "horizon_capacity_p50": 13,
    "horizon_shortfall_probability": 0.774,
    "maximum_shortfall_probability": 0.774,
    "required_capacity": 15,
    "starting_capacity": 20
  },
  "expected_capacity_loss_by_cause": [
    {
      "event_type": "voluntary_exit",
      "expected_capacity_loss": 7.242
    }
  ],
  "interpretation": "This is aggregate role-capacity risk, not an attrition score for a named person. It cannot identify who will leave or justify employment action.",
  "method": "hierarchical_dirichlet_competing_workforce_capacity_simulation_v1",
  "period_forecast": [
    {
      "capacity_p10": 18,
      "capacity_p50": 19,
      "capacity_p90": 20,
      "confidence_interval": [
        17,
        20
      ],
      "period": 0,
      "probability_capacity_shortfall": 0.002,

How it works

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

1. 1 Convert each historical role spell into period-at-risk outcomes—one declared cause or continued exposure—while retaining right-censored spells rather than treating them as non-events.
2. 2 Estimate organization-period Dirichlet outcome distributions, then partially pool each role-period distribution toward them using the governed prior strength; carry the last supported organization hazard into explicitly labeled unsupported future periods.
3. 3 For every simulation, draw role-period competing-risk probabilities and remove aggregate positions once across causes using conditional multinomial sampling, preserving that one position cannot experience two exits.
4. 4 Translate surviving positions to capacity, compare role and total capacity with governed requirements by period, and return shortfall probabilities, quantiles, cause-attributed expected loss, unseen-role flags, and extrapolation warnings.

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": "forecast aggregate rolecapacity shortfall with a" }
  → finds "forecast_aggregate_workforce_capacity_risk"

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

gitrevio_capability_run
  { "capability_id": "forecast_aggregate_workforce_capacity_risk", "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 →