Build reverse stress scenarios

What it's for

Lets boards and investors ask what smallest combination of demand, cost, delivery, reliability, or financing shocks would break a critical requirement—before ordinary forecasts show distress.

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_outcome": 100,
  "drivers": [
    {
      "adverse_outcome_change_per_unit": 2,
      "id": "demand-loss",
      "maximum_adverse_shock": 15,
      "shock_scale": 5
    },
    {
      "adverse_outcome_change_per_unit": 1,
      "id": "cost-inflation",
      "maximum_adverse_shock": 20,
      "shock_scale": 8
    },
    {
      "adverse_outcome_change_per_unit": 3,
      "id": "delivery-delay",
      "maximum_adverse_shock": 6,
      "shock_scale": 2
    }
  ],
  "failure_threshold": 70,
  "maximum_plausible_standardized_distance": 3
}

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": [
    "Adverse effects are locally linear and additive within stated bounds, with scale defining standardized shock distance.",
    "The minimum-distance scenario is an optimization result, not a probability forecast or prediction that drivers will move together.",
    "Owners must separately test nonlinearities, feedback, dependence, omitted drivers, and multiple failure modes."
  ],
  "decision": "failure_within_governed_plausibility_envelope",
  "driver_diagnostics": [
    {
      "adverse_shock": 7.5,
      "bound_binding": false,
      "driver_id": "demand-loss",
      "maximum_adverse_shock": 15,
      "outcome_loss_contribution": 15,
      "share_of_required_loss": 0.5,
      "shock_in_scale_units": 1.5,
      "single_driver_shock_to_failure": 15
    },
    {
      "adverse_shock": 9.6,
      "bound_binding": false,
      "driver_id": "cost-inflation",
      "maximum_adverse_shock": 20,
      "outcome_loss_contribution": 9.6,
      "share_of_required_loss": 0.32,
      "shock_in_scale_units": 1.2,
      "single_driver_shock_to_failure": null
    },
    {
      "adverse_shock": 1.8,
      "bound_binding": false,
      "driver_id": "delivery-delay",
      "maximum_adverse_shock": 6,
      "outcome_loss_contribution": 5.4,
      "share_of_required_loss": 0.18,
      "shock_in_scale_units": 0.9,
      "single_driver_shock_to_failure": null
    }
  ],
  "method": "bounded_l2_reverse_stress_v1",
  "summary": {
    "achieved_outcome_loss": 30,
    "base_outcome": 100,
    "binding_driver_count": 0,

How it works

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

1. 1 Freeze the base outcome, failure threshold, locally adverse driver sensitivities, maximum shocks, scale units, and plausibility distance before optimization.
2. 2 Check whether maximum bounded shocks can reach failure, then solve the convex weighted-L2 reverse-stress problem by capped KKT water filling and verify the stressed outcome hits the threshold.
3. 3 Expose the minimum joint shock, driver loss contributions, binding limits and single-driver breakpoints, labeling distance as geometry rather than 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": "solve the minimum standardized bounded combination" }
  → finds "build_reverse_stress_scenarios"

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

gitrevio_capability_run
  { "capability_id": "build_reverse_stress_scenarios", "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 Finance & unit economics →