Forecast operational recovery half life

What it's for

Turns resilience from a backward-looking uptime number into a forward operating forecast: executives and investors can see recovery half-life, confidence of restoring required performance, and the economic area under the disruption curve.

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_shocks": [
    {
      "current_performance_fraction": 0.2,
      "id": "current-high",
      "required_performance_fraction": 0.8,
      "severity": "high",
      "value_loss_per_fraction_period": 1000
    }
  ],
  "historical_recoveries": [
    {
      "elapsed_periods": 0,
      "id": "recovery-0-0",
      "performance_fraction": 0.19999999999999996,
      "severity": "low",
      "shock_id": "shock-0"
    },
    {
      "elapsed_periods": 1,
      "id": "recovery-0-1",
      "performance_fraction": 0.4343145750507619,
      "severity": "low",
      "shock_id": "shock-0"
    },
    {
      "elapsed_periods": 2,
      "id": "recovery-0-2",
      "performance_fraction": 0.6,
      "severity": "low",
      "shock_id": "shock-0"
    },
    {
      "elapsed_periods": 3,
      "id": "recovery-0-3",
      "performance_fraction": 0.7171572875253809,
      "severity": "low",
      "shock_id": "shock-0"
    },
    {
      "elapsed_periods": 4,
      "id": "recovery-0-4",
      "performance_fraction": 0.8,
      "severity": "low",

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": [
    "Within a stable severity/response epoch, remaining performance loss decays approximately exponentially and historical recovery trajectories are comparable to current shocks.",
    "Performance fractions share one baseline and required-service interpretation, stalled histories are retained at the governed half-life cap, and censoring is not silently treated as recovery.",
    "Severity pooling, current performance, recovery requirements, and value conversion are organization-owned and validated on later shocks."
  ],
  "current_shock_forecast": [
    {
      "half_life_interval": [
        3.4929,
        7.6893
      ],
      "historical_severity_support": 10,
      "median_recovery_period": 8,
      "probability_recovered_within_horizon": 0.218,
      "severity": "high",
      "shock_id": "current-high"
    }
  ],
  "decision": "aggregate_recovery_capacity_risk_material",
  "executive_summary": {
    "cumulative_value_loss_interval": [
      2654.4651,
      4544.0907
    ],
    "expected_cumulative_value_loss": 3625.1786,
    "historical_stalled_fraction": 0,
    "probability_all_recovered_within_horizon": 0.218,
    "target_all_recovered_probability": 0.8,
    "unseen_current_severities": []
  },
  "historical_recovery_diagnostics": [
    {
      "half_life": 2,
      "log_gap_rmse": 0,
      "severity": "low",
      "shock_id": "shock-0",
      "stalled_or_nonrecovering": false
    },
    {
      "half_life": 6,
      "log_gap_rmse": 0,
      "severity": "high",
      "shock_id": "shock-1",

How it works

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

1. 1 Build version-consistent shock trajectories with a common performance baseline, severity, cadence, period zero, and at least three pre-ceiling recovery observations; preserve stalled and unresolved behavior rather than keeping successful recoveries only.
2. 2 Fit log remaining-performance loss against elapsed time inside each historical shock, convert negative slopes to half-life, cap stalled/nonrecovering slopes visibly, and partially pool severity log half-life mean/variance toward the organization-wide reference.
3. 3 Draw severity-specific half-lives for each current shock, continue its observed performance gap over the decision horizon, test its governed required-performance floor, and aggregate performance and value-loss paths while disclosing unseen-severity fallback.
4. 4 Report joint probability all current shocks recover, period distributions, per-shock recovery timing, historical stalls, model support, and explicit abstention when recovery capacity does not clear the owner-set confidence target.

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 how quickly operational performance recovers" }
  → finds "forecast_operational_recovery_half_life"

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

gitrevio_capability_run
  { "capability_id": "forecast_operational_recovery_half_life", "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 Org design, incentives & decisions →