Optimize shared assumption hedging portfolio

What it's for

Does more than identify a common strategic weak point: it chooses the best affordable combination of experiments, options, diversification and mitigations, crediting one action for value protected across every dependent initiative.

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": [
    {
      "id": "adoption",
      "retained_value_fraction_scenarios": [
        0.8,
        0.4
      ]
    },
    {
      "id": "price",
      "retained_value_fraction_scenarios": [
        0.9,
        0.5
      ]
    }
  ],
  "hedge_budget": 3,
  "hedge_capacity_units": 2,
  "initiatives": [
    {
      "approved_value_scenarios": [
        100,
        80
      ],
      "assumption_ids": [
        "adoption",
        "price"
      ],
      "id": "shared-platform"
    },
    {
      "approved_value_scenarios": [
        60,
        40
      ],
      "assumption_ids": [
        "adoption"
      ],
      "id": "enterprise-product"
    }
  ],
  "interventions": [
    {

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": "adoption",
      "expected_baseline_retained_value_fraction": 0.68,
      "expected_selected_retained_value_fraction": 0.9,
      "linked_initiative_count": 2,
      "selected_intervention_ids": [
        "adoption-pilot"
      ]
    },
    {
      "assumption_id": "price",
      "expected_baseline_retained_value_fraction": 0.78,
      "expected_selected_retained_value_fraction": 0.89,
      "linked_initiative_count": 1,
      "selected_intervention_ids": [
        "pricing-research"
      ]
    }
  ],
  "configuration": {
    "hedge_budget": 3,
    "hedge_capacity_units": 2,
    "maximum_acceptable_cvar_loss": null,
    "minimum_expected_net_value": 0,
    "minimum_probability_positive_net_value": 0.5,
    "risk_aversion": 0,
    "scenario_count": 2,
    "tail_probability": 0.3
  },
  "decision": "shared_assumption_hedging_portfolio_supported",
  "guardrails": [
    "An intervention must have a prospectively estimated local effect on the remaining downside of one assumption. Multiple actions close that remaining gap with diminishing returns; they are never added as independent percentage-point gains.",
    "One improved shared premise can recover value in several initiatives, while initiatives with several necessary premises create complementarity. Common scenarios preserve effect, cost and portfolio dependence that standalone ROI rankings discard.",
    "Exact mode proves optimality only for the represented actions, constraints and scenarios; beam mode does not. Selection cannot bypass causal evidence, finance, liquidity, legal, security, safety, privacy or accountable human approval."
  ],
  "method": "dependency_aware_nonlinear_shared_assumption_hedge_portfolio_v1",
  "selected_interventions": [
    {
      "assumption_id": "adoption",
      "budget_cost": 2,
      "capacity_units": 1,
      "dependency_closed_leave_one_out_expected_net_value_loss": 25.86,

How it works

Constrained optimization — Pick the best feasible option under real limits — budget, headcount, dependencies, capacity — rather than ranking a list and hoping it fits.

1. 1 Freeze the shared-assumption portfolio model and define each executable action by one targeted premise, conditional remaining-gap closure, common-scenario full cost, budget/capacity use, dependencies and exclusions.
2. 2 For every feasible action set, combine repeated premise actions multiplicatively on the remaining downside, recompute every linked initiative's joint retained value and subtract scenario-aligned costs.
3. 3 Maximize expected net recovered value minus a CVaR penalty subject to positive-value and tail-loss gates, returning an exact certificate within the state boundary or an explicit deterministic dependency-closed beam fallback.

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": "choose a budgeted capacityfeasible portfolio of" }
  → finds "optimize_shared_assumption_hedging_portfolio"

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

gitrevio_capability_run
  { "capability_id": "optimize_shared_assumption_hedging_portfolio", "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 Analytics assurance & orchestration →