Forecast hiring ramp capacity

What it's for

Supplies the probabilistic hiring side of the What-If Simulator with organization-calibrated ramp curves, onboarding drag, p10/p50/p90 capacity, and financial break-even rather than a universal time-to-productivity constant.

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.

{
  "base_team_capacity_per_period": 20,
  "capacity_value_per_unit": 100,
  "historical_ramp_observations": [
    {
      "days_since_start": 30,
      "hire_id": "historical-hire-0",
      "id": "ramp-example-0-30",
      "productive_capacity_fraction": 0.3934693402873666,
      "role_id": "backend"
    },
    {
      "days_since_start": 60,
      "hire_id": "historical-hire-0",
      "id": "ramp-example-0-60",
      "productive_capacity_fraction": 0.6321205588285577,
      "role_id": "backend"
    },
    {
      "days_since_start": 90,
      "hire_id": "historical-hire-0",
      "id": "ramp-example-0-90",
      "productive_capacity_fraction": 0.7768698398515702,
      "role_id": "backend"
    },
    {
      "days_since_start": 120,
      "hire_id": "historical-hire-0",
      "id": "ramp-example-0-120",
      "productive_capacity_fraction": 0.8646647167633873,
      "role_id": "backend"
    },
    {
      "days_since_start": 30,
      "hire_id": "historical-hire-1",
      "id": "ramp-example-1-30",
      "productive_capacity_fraction": 0.3934693402873666,
      "role_id": "backend"
    },
    {
      "days_since_start": 60,
      "hire_id": "historical-hire-1",
      "id": "ramp-example-1-60",
      "productive_capacity_fraction": 0.6321205588285577,

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": [
    "Ramp time is lognormal across hires and the productive-capacity curve follows the governed Weibull shape.",
    "Historical capacity fractions are comparable aggregate measurements, not person-level performance scores.",
    "Capacity value, mentor load, costs, planned start dates, and targets are organization-owned scenarios."
  ],
  "configuration": {
    "horizon_periods": 6,
    "organization_shock_sd": 0.15,
    "period_days": 30,
    "role_prior_strength": 3,
    "simulations": 500,
    "weibull_shape": 1
  },
  "decision": "hiring_plan_forecast_ready",
  "detail_counts": {
    "planned_hires": 1,
    "role_calibrations": 2
  },
  "economics": {
    "financial_break_even_period_p50": 0,
    "npv_p10": 1575.2225,
    "npv_p50": 2084.7383,
    "npv_p90": 2467.9205,
    "total_planned_cost": 340
  },
  "executive_summary": {
    "median_horizon_incremental_capacity": 24.9275,
    "median_plan_npv": 2084.7383,
    "planned_hires": 1,
    "probability_capacity_break_even_within_horizon": 1,
    "probability_financial_break_even_within_horizon": 1,
    "probability_positive_npv": 1
  },
  "interpretation": "This forecasts an aggregate hiring plan and its onboarding load. It does not rank candidates or promise that a named person will follow the role-level ramp distribution.",
  "method": "hierarchical_lognormal_weibull_hiring_ramp_simulation_v1",
  "period_forecast": [
    {
      "capacity_p10": 20.89,
      "capacity_p50": 21.6083,
      "capacity_p90": 22.4487,
      "confidence_interval": [
        20.7769,
        22.7339

How it works

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

1. 1 Transform each historical capacity observation through the governed Weibull ramp curve to estimate one robust log ramp-time value per historical hire.
2. 2 Partially pool role-level log ramp times toward the organization distribution so sparse roles widen uncertainty instead of inheriting brittle point estimates.
3. 3 Simulate planned role capacity with idiosyncratic lognormal ramp times plus a shared organization shock, then subtract exponentially decaying mentor load at every period.
4. 4 Compare capacity bands with declared commitments and discount locally valued incremental capacity against upfront and recurring hiring-plan costs to estimate NPV and break-even probability.

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 an aggregate hiring plan with" }
  → finds "forecast_hiring_ramp_capacity"

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

gitrevio_capability_run
  { "capability_id": "forecast_hiring_ramp_capacity", "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 →