Rank initiatives evidence adjusted value

What it's for

Stops spectacular but weakly supported business cases from outranking credible value simply because their spreadsheet forecast is larger.

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.

{
  "initiatives": [
    {
      "evidence_reliability": 0.85,
      "id": "credible-core",
      "implementation_cost": 100,
      "incremental_value_scenarios": [
        240,
        180,
        120
      ]
    },
    {
      "evidence_reliability": 0.25,
      "id": "weak-moonshot",
      "implementation_cost": 100,
      "incremental_value_scenarios": [
        600,
        350,
        100
      ]
    }
  ],
  "scenario_probabilities": [
    0.2,
    0.5,
    0.3
  ],
  "skeptical_prior_incremental_value": 0
}

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": [
    "Incremental value scenarios use one finance-approved counterfactual, currency, horizon, attribution boundary, and joint scenario definition; implementation cost is fully loaded and non-overlapping.",
    "Evidence reliability is a governed, backtested probability that the submitted value model is decision-relevant; it is not confidence, sample size, or stakeholder enthusiasm by another name.",
    "The skeptical-prior mixture makes weak evidence explicit and portable but does not replace causal validation, strategic constraints, dependency analysis, or portfolio optimization."
  ],
  "configuration": {
    "cvar_penalty_weight": 0.25,
    "maximum_negative_net_value_probability": 0.5,
    "minimum_evidence_reliability": 0.5,
    "scenario_count": 3,
    "skeptical_prior_incremental_value": 0,
    "tail_probability": 0.1
  },
  "decision": "evidence_adjusted_initiatives_supported",
  "initiative_ranking": [
    {
      "clears_evidence_and_value_gates": true,
      "cvar_net_value_loss": 100,
      "evidence_adjustment": -26.1,
      "evidence_reliability": 0.85,
      "expected_evidence_adjusted_net_value": 47.9,
      "expected_observed_net_value": 74,
      "implementation_cost": 100,
      "initiative_id": "credible-core",
      "probability_negative_net_value": 0.15,
      "risk_adjusted_value_score": 22.9
    },
    {
      "clears_evidence_and_value_gates": false,
      "cvar_net_value_loss": 100,
      "evidence_adjustment": -243.75,
      "evidence_reliability": 0.25,
      "expected_evidence_adjusted_net_value": -18.75,
      "expected_observed_net_value": 225,
      "implementation_cost": 100,
      "initiative_id": "weak-moonshot",
      "probability_negative_net_value": 0.75,
      "risk_adjusted_value_score": -43.75
    }
  ],
  "method": "evidence_mixture_risk_adjusted_initiative_ranking_v1",
  "summary": {
    "initiative_count": 2,

How it works

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

1. 1 Freeze incremental value scenarios, fully loaded cost, one counterfactual and horizon, plus a prospectively defined evidence-reliability measure calibrated on resolved business cases.
2. 2 Mix each initiative's scenario distribution with the skeptical prior using reliability as probability mass, then calculate adjusted expected net value, loss probability, CVaR, and risk-adjusted score.
3. 3 Rank only initiatives clearing reliability, positive-value, and downside gates; route dependencies, constraints, and mutually exclusive choices to a portfolio optimizer rather than treating rank as allocation.

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": "rank initiatives using an explicit mixture" }
  → finds "rank_initiatives_evidence_adjusted_value"

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

gitrevio_capability_run
  { "capability_id": "rank_initiatives_evidence_adjusted_value", "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 →