Forecast correlated milestone slippage

What it's for

Gives executives and investors a portfolio-level answer ordinary project trackers cannot: the probability every linked milestone lands, how common shocks cascade through dependencies, and how much value sits in the tail.

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.

{
  "current_milestones": [
    {
      "category": "platform",
      "deadline_days": 12,
      "id": "foundation",
      "remaining_duration_days": 12,
      "requires": [],
      "value_at_risk": 100
    },
    {
      "category": "product",
      "deadline_days": 24,
      "id": "launch",
      "remaining_duration_days": 12,
      "requires": [
        "foundation"
      ],
      "value_at_risk": 200
    },
    {
      "category": "security",
      "deadline_days": 36,
      "id": "assurance",
      "remaining_duration_days": 12,
      "requires": [
        "launch"
      ],
      "value_at_risk": 300
    }
  ],
  "historical_milestones": [
    {
      "actual_duration_days": 10,
      "category": "product",
      "episode_id": "episode-0",
      "id": "milestone-history-0-product",
      "planned_duration_days": 10
    },
    {
      "actual_duration_days": 10.696352246247812,
      "category": "platform",
      "episode_id": "episode-0",
      "id": "milestone-history-0-platform",

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": [
    "Historical planned-versus-actual duration ratios are comparable to current remaining-duration estimates within a stable planning and delivery epoch.",
    "The shrinkage Gaussian copula and governed portfolio-shock fraction adequately represent dependence, while the dependency DAG captures prerequisite timing.",
    "Deadlines and value-at-risk amounts are owner-governed and do not double count dependent milestone value."
  ],
  "correlation_diagnostics": [
    {
      "left_category": "platform",
      "right_category": "product",
      "shrunk_correlation": 0.7751
    },
    {
      "left_category": "platform",
      "right_category": "security",
      "shrunk_correlation": 0.7748
    },
    {
      "left_category": "product",
      "right_category": "security",
      "shrunk_correlation": 0.7233
    }
  ],
  "decision": "correlated_portfolio_slippage_risk_material",
  "executive_summary": {
    "conditional_tail_value_at_risk": 600,
    "correlation_joint_probability_delta": 0.112,
    "expected_value_at_risk": 311.6,
    "independent_joint_on_time_probability": 0.256,
    "joint_on_time_probability": 0.368,
    "portfolio_finish_day_p50": 36.3855,
    "portfolio_finish_day_p90": 46.3225,
    "target_joint_on_time_probability": 0.8,
    "value_at_risk_quantile": 600
  },
  "limitations": [
    "This is a reference-class slippage forecast, not a causal diagnosis of why a team or milestone is late.",
    "Unseen categories use a disclosed global fallback; novel shocks, scope changes, resource contention, and feedback can exceed historical tails.",
    "Correlation is not causation, and the independent comparison is a sensitivity baseline rather than the true counterfactual portfolio."
  ],
  "method": "shrinkage_gaussian_copula_dependency_milestone_forecast_v1",
  "milestone_forecast": [
    {
      "category": "platform",

How it works

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

1. 1 Build complete historical portfolio episodes containing one planned and actual duration for every governed milestone category; model their log duration ratios and reject constant, sparse, or incomplete category histories.
2. 2 Estimate category location/scale and cross-category dependence, shrink the empirical correlation toward independence, project it to a positive-definite correlation matrix, and combine a governed shared-shock fraction with milestone-specific noise.
3. 3 Draw correlated duration multipliers, fall back visibly to the global history for unseen categories, and evaluate every simulation in dependency-topological order so prerequisite slippage propagates to downstream finish dates.
4. 4 Compare joint on-time confidence with the governed commitment target and an independent-shock sensitivity baseline; report milestone miss probabilities, portfolio finish tails, expected loss, VaR, and conditional tail value at risk.

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": "forecast joint portfolio milestone slippage from" }
  → finds "forecast_correlated_milestone_slippage"

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

gitrevio_capability_run
  { "capability_id": "forecast_correlated_milestone_slippage", "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 Delivery forecasting & commitments →