Audit scenario tree decision integrity

What it's for

Lets a CEO, board or investor distinguish a genuinely adaptive plan from a spreadsheet that quietly chooses today using tomorrow's information.

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.

{
  "scenario_paths": [
    {
      "action_ids_by_stage": [
        "reserve-capacity",
        "slow-roadmap"
      ],
      "action_information_dependencies_by_stage": [
        [],
        [
          "demand"
        ]
      ],
      "evidence_verified": true,
      "id": "policy-low",
      "node_path": [
        "root",
        "low-demand"
      ],
      "policy_id": "adaptive-roadmap",
      "probability": 0.4,
      "revealed_information_by_stage": [
        [],
        [
          "demand"
        ]
      ],
      "scenario_id": "low-demand"
    },
    {
      "action_ids_by_stage": [
        "reserve-capacity",
        "scale-roadmap"
      ],
      "action_information_dependencies_by_stage": [
        [],
        [
          "demand"
        ]
      ],
      "evidence_verified": true,
      "id": "policy-high",
      "node_path": [
        "root",

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.

{
  "configuration": {
    "minimum_terminal_scenarios_per_policy": 2,
    "probability_tolerance": 0
  },
  "decision": "scenario_tree_decision_integrity_supported",
  "guardrails": [
    "A decision at a node may use only information released by that node and must be identical for every terminal scenario sharing that history. Scenario-specific actions before their distinguishing signal are clairvoyance, not management flexibility.",
    "Terminal probabilities, node identities, action provenance and information-release times must come from one frozen scenario-tree version. The audit does not certify the probabilities or economic assumptions themselves.",
    "Failures diagnose an aggregate planning artifact. They are not evidence of fraud, employee misconduct or intent, and must not be used for individual employment or security decisions."
  ],
  "method": "scenario_tree_probability_information_nonanticipativity_audit",
  "policy_diagnostics": [
    {
      "ambiguous_node_ids": [],
      "decision": "scenario_tree_policy_integrity_supported",
      "failed_checks": [],
      "future_information_dependencies": [],
      "inconsistent_information_nodes": [],
      "nonanticipativity_violation_nodes": [],
      "policy_id": "adaptive-roadmap",
      "probability_mass": 1,
      "stage_count": 2,
      "terminal_scenario_count": 2,
      "unverified_probability_mass": 0
    }
  ],
  "summary": {
    "action_required_policy_count": 0,
    "ambiguous_node_id_count": 0,
    "future_information_dependency_count": 0,
    "information_set_inconsistency_count": 0,
    "nonanticipativity_violation_node_count": 0,
    "policy_count": 1,
    "summed_unverified_probability_mass": 0,
    "supported_policy_count": 1
  },
  "truncation": {
    "policies_omitted": 0
  }
}

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 each policy, terminal scenario, probability, ordered node history, action sequence, information-release sequence and declared action-information dependency from one immutable scenario-tree version.
2. 2 Within each policy, reconcile probability mass, stage alignment, one root and unique node ancestry; then group terminal paths by every shared prefix and verify that both available information and chosen action are identical at the decision node.
3. 3 Accumulate information only when released, flag dependencies on unavailable future signals, preserve unverified probability mass and withhold integrity whenever support, probability, ancestry, evidence, information timing or nonanticipativity fails.

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": "audit whether an adaptive management or" }
  → finds "audit_scenario_tree_decision_integrity"

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

gitrevio_capability_run
  { "capability_id": "audit_scenario_tree_decision_integrity", "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 →