Audit fundraising pipeline integrity

What it's for

Makes a board fundraising pipeline auditable: leaders can see whether reported stage, proceeds and close probabilities were genuinely point-in-time and calibrated before runway decisions depend on them.

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_day": 20,
  "opportunities": [
    {
      "actual_primary_proceeds": 100,
      "evidence_verified": true,
      "forecast_as_of_day": 1,
      "forecast_close_probability": 0.5,
      "forecast_horizon_days": 10,
      "id": "resolved-0",
      "investor_account_id": "investor-0",
      "opened_day": 0,
      "resolved_day": 5,
      "stage_events": [
        {
          "day": 1,
          "stage": "contacted"
        },
        {
          "day": 2,
          "stage": "diligence"
        },
        {
          "day": 3,
          "stage": "term_sheet"
        }
      ],
      "status": "won"
    },
    {
      "actual_primary_proceeds": 100,
      "evidence_verified": true,
      "forecast_as_of_day": 1,
      "forecast_close_probability": 0.5,
      "forecast_horizon_days": 10,
      "id": "resolved-1",
      "investor_account_id": "investor-1",
      "opened_day": 0,
      "resolved_day": 5,
      "stage_events": [
        {
          "day": 1,
          "stage": "contacted"
        },

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.

{
  "calibration_bins": [
    {
      "forecast_count": 20,
      "lower_probability": 0.4,
      "mean_forecast_probability": 0.5,
      "observed_close_rate": 0.5,
      "upper_probability": 0.6
    }
  ],
  "decision": "fundraising_pipeline_decision_grade",
  "guardrails": [
    "Only forecasts frozen before resolution enter calibration, and active opportunities become negative labels only after their declared horizon matures. Open cases are otherwise retained as censored rather than relabeled as failures.",
    "Duplicate active investor-account records, missing evidence, late forecasts, impossible proceeds, and broken event time are data-integrity failures, not evidence about an investor or employee's intent.",
    "Pipeline calibration is organization-, stage-, market-, and process-specific. It is not a securities, fundraising, investor-quality, or financing-availability opinion."
  ],
  "method": "point_in_time_fundraising_event_and_probability_integrity_audit",
  "opportunity_diagnostics": [
    {
      "current_stage": "term_sheet",
      "days_in_pipeline": 20,
      "failed_checks": [],
      "forecast_close_probability": 0.5,
      "forecast_mature": true,
      "forecast_outcome": 1,
      "investor_account_id": "investor-0",
      "opportunity_id": "resolved-0",
      "status": "won"
    },
    {
      "current_stage": "term_sheet",
      "days_in_pipeline": 20,
      "failed_checks": [],
      "forecast_close_probability": 0.5,
      "forecast_mature": true,
      "forecast_outcome": 1,
      "investor_account_id": "investor-1",
      "opportunity_id": "resolved-1",
      "status": "won"
    },
    {
      "current_stage": "term_sheet",
      "days_in_pipeline": 20,
      "failed_checks": [],

How it works

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

1. 1 Freeze the stage taxonomy, as-of date, immutable stage events, terminal outcomes, actual primary proceeds and the close-probability forecast that existed before each outcome.
2. 2 Reconstruct each opportunity, checking entry stage, strict event time, forward stage progression, active/terminal consistency, primary-proceeds identity, evidence and duplicate live investor accounts.
3. 3 Label won or lost opportunities at their declared forecast horizon, retain not-yet-mature active cases as censored, then calculate Brier loss, calibration-in-the-large and fixed probability-bin reliability before applying support and quality gates.

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 a fundraising pipeline as pointintime" }
  → finds "audit_fundraising_pipeline_integrity"

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

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