Stress test investment memo assumptions

What it's for

Shows exactly how much simultaneous deterioration an investment thesis can absorb and where weak evidence or nonlinear interactions break it.

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": 0.1,
      "evidence_reliability": 0.9,
      "id": "growth",
      "nominal_value": 0.3,
      "value_sensitivity": 100
    },
    {
      "adverse_value": 0.5,
      "evidence_reliability": 0.8,
      "id": "margin",
      "nominal_value": 0.7,
      "value_sensitivity": 80
    }
  ],
  "base_case_value": 150,
  "interactions": [
    {
      "assumption_a": "growth",
      "assumption_b": "margin",
      "value_interaction_coefficient": -200
    }
  ],
  "minimum_acceptable_value": 100,
  "required_robustness_fraction": 0.8
}

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": [
    {
      "assumption_id": "growth",
      "evidence_adjustment_value_impact": -2,
      "evidence_reliability": 0.9,
      "one_at_a_time_adverse_value_impact": -20
    },
    {
      "assumption_id": "margin",
      "evidence_adjustment_value_impact": -3.2,
      "evidence_reliability": 0.8,
      "one_at_a_time_adverse_value_impact": -16
    }
  ],
  "assumptions": [
    "The supplied sensitivities and pairwise interactions are a local value model around the base case, not globally valid causal effects; units and nonlinear terms are finance-reviewed.",
    "Each declared adverse value must weakly reduce value in isolation, evidence reliability is calibrated on resolved comparable claims, and weak evidence moves the nominal assumption toward its adverse value.",
    "The robustness fraction is the first failure along the declared simultaneous adverse path; omitted assumptions, higher-order interactions, probability, financing availability, and legal/tax effects are not covered."
  ],
  "configuration": {
    "assumption_count": 2,
    "interaction_count": 1,
    "required_robustness_fraction": 0.8
  },
  "decision": "investment_memo_assumptions_robust",
  "method": "reliability_adjusted_nonlinear_investment_memo_stress_v1",
  "summary": {
    "adverse_path_robustness_fraction": 1,
    "base_case_value": 150,
    "clears_evidence_adjusted_value_gate": true,
    "clears_robustness_fraction_gate": true,
    "evidence_adjusted_value": 144.64,
    "joint_adverse_value": 106,
    "minimum_acceptable_value": 100
  },
  "truncated_assumption_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 investment-value perimeter, minimum acceptable value, assumption units, nominal and adverse values, local sensitivities, evidence reliabilities, and finance-reviewed pairwise interactions before seeing the answer.
2. 2 Move weakly evidenced nominal claims toward their adverse values, calculate one-at-a-time and nonlinear joint impacts, and trace the simultaneous adverse path to its first threshold crossing.
3. 3 Support the memo only when evidence-adjusted value and the governed required robustness fraction both clear, while treating omitted assumptions and model-form error as outside the certificate.

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 an investment memos local value" }
  → finds "stress_test_investment_memo_assumptions"

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

gitrevio_capability_run
  { "capability_id": "stress_test_investment_memo_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 Investment & portfolio choice →