Stress test operating plan assumptions

What it's for

Shows executives exactly which assumptions consume operating-plan headroom and how far the encoded plan can move toward its adverse bounds before failure.

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.

{
  "assumptions": [
    {
      "adverse_value": 6,
      "baseline_value": 10,
      "id": "growth",
      "outcome_change_per_unit": 3
    },
    {
      "adverse_value": 6,
      "baseline_value": 4,
      "id": "margin",
      "outcome_change_per_unit": -5
    },
    {
      "adverse_value": 5,
      "baseline_value": 10,
      "id": "hiring",
      "outcome_change_per_unit": 1
    }
  ],
  "base_outcome": 100,
  "minimum_acceptable_outcome": 70
}

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.

{
  "assumption_diagnostics": [
    {
      "adverse_value": 6,
      "assumption_id": "growth",
      "baseline_value": 10,
      "fraction_of_adverse_range_to_failure": 2.5,
      "full_adverse_outcome_impact": -12,
      "individual_failure_reached": false,
      "individual_stressed_outcome": 88,
      "outcome_change_per_unit": 3
    },
    {
      "adverse_value": 6,
      "assumption_id": "margin",
      "baseline_value": 4,
      "fraction_of_adverse_range_to_failure": 3,
      "full_adverse_outcome_impact": -10,
      "individual_failure_reached": false,
      "individual_stressed_outcome": 90,
      "outcome_change_per_unit": -5
    },
    {
      "adverse_value": 5,
      "assumption_id": "hiring",
      "baseline_value": 10,
      "fraction_of_adverse_range_to_failure": 6,
      "full_adverse_outcome_impact": -5,
      "individual_failure_reached": false,
      "individual_stressed_outcome": 95,
      "outcome_change_per_unit": 1
    }
  ],
  "assumptions": [
    "Baseline and adverse values are finance-owned plausible bounds over one horizon, while sensitivities are locally validated directional outcome responses rather than raw correlations.",
    "The common-range breakpoint scales all encoded adverse shifts together in a linear additive model; it is geometry, not a probability or forecast.",
    "Interactions, thresholds, feedback, adaptation, financing, and omitted assumptions remain outside the result and require scenario or simulation follow-up."
  ],
  "configuration": {
    "linear_additive_stress_model": true,
    "material_headroom_fraction": 0.1
  },
  "decision": "operating_plan_assumption_headroom_supported",
  "method": "operating_plan_linear_assumption_breakpoint_stress_v1",

How it works

Decision analysis — Turn uncertainty, cost and risk appetite into a defensible choice, with the reasoning left inspectable.

1. 1 Freeze the plan outcome, minimum acceptable outcome, finance-owned plausible baseline/adverse bounds, and locally validated directional outcome sensitivity for every material assumption.
2. 2 Calculate one-at-a-time adverse impacts, their additive joint outcome, remaining headroom, and the common fraction of all encoded adverse ranges required to reach failure.
3. 3 Rank assumption contributions and route material plans to nonlinear interaction, feedback, financing, and adaptation scenarios rather than interpreting a linear breakpoint as 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": "stress every operatingplan assumption individually and" }
  → finds "stress_test_operating_plan_assumptions"

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

gitrevio_capability_run
  { "capability_id": "stress_test_operating_plan_assumptions", "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 Risk, tails & resilience →