Audit strategic assumption lineage

What it's for

Shows boards and investors when apparently independent bets secretly rest on the same stale growth, adoption, price, staffing or platform premise—and exactly how much approved value lacks clean lineage.

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.

{
  "as_of_period": 10,
  "assumptions": [
    {
      "canonical_value": 0.6,
      "evidence_ids": [
        "pilot-2026",
        "customer-study-2026"
      ],
      "evidence_verified": true,
      "id": "enterprise-adoption",
      "last_validated_period": 9,
      "unit": "fraction",
      "version": "v2"
    }
  ],
  "claims": [
    {
      "assumption_id": "enterprise-adoption",
      "assumption_version": "v2",
      "exposed_value": 100,
      "id": "platform-adoption-claim",
      "initiative_id": "shared-platform",
      "unit": "fraction",
      "used_value": 0.6
    }
  ],
  "maximum_single_assumption_exposure_fraction": 1
}

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": "enterprise-adoption",
      "claim_count": 1,
      "evidence_source_count": 2,
      "evidence_verified": true,
      "known_assumption": true,
      "linked_initiative_count": 1,
      "portfolio_exposure_fraction": 1,
      "reused_evidence_ids": [],
      "shared_across_initiatives": false,
      "stale": false,
      "total_exposed_value": 100,
      "unit": "fraction",
      "version": "v2"
    }
  ],
  "claim_diagnostics": [
    {
      "assumption_id": "enterprise-adoption",
      "claim_id": "platform-adoption-claim",
      "exposed_value": 100,
      "initiative_id": "shared-platform",
      "lineage_flags": [],
      "used_value_relative_error": 0
    }
  ],
  "configuration": {
    "as_of_period": 10,
    "maximum_assumption_age_periods": 4,
    "maximum_conflicting_exposure_fraction": 0.05,
    "maximum_reused_evidence_exposure_fraction": 0.25,
    "maximum_single_assumption_exposure_fraction": 1,
    "maximum_stale_exposure_fraction": 0.05,
    "maximum_unverified_exposure_fraction": 0.05,
    "maximum_used_value_relative_error": 0.02,
    "minimum_independent_evidence_sources": 1
  },
  "decision": "strategic_assumption_lineage_supported",
  "failed_gates": [],
  "guardrails": [
    "Claims are aggregate initiative-value exposures, not employee output. A shared assumption is not automatically invalid; it becomes a portfolio concentration that must have explicit lineage, ownership, versioning and evidence.",
    "Evidence IDs must represent genuinely independent source lineages. Renaming, copying or reformatting one source does not create independent evidence, and this audit cannot detect undisclosed common ancestry.",

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 as-of period and join every aggregate initiative-value exposure to its canonical assumption ID, version, value, unit, validation period and immutable evidence-source IDs.
2. 2 Flag unknown links, version/unit/value conflicts, stale validation, unverified or insufficient evidence and common evidence ancestry without dropping affected value from the denominator.
3. 3 Aggregate affected exposure and linked initiatives by assumption, then gate each exposure class and the largest shared-premise concentration under organization-owned tolerances.

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 every aggregate initiativevalue claim against" }
  → finds "audit_strategic_assumption_lineage"

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

gitrevio_capability_run
  { "capability_id": "audit_strategic_assumption_lineage", "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 →