Optimize decision calendar

What it's for

Creates an executive decision calendar that knows when waiting buys useful evidence, when delay destroys value, and which decisions compete for the same leadership attention.

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.

{
  "calendar_periods": [
    {
      "decision_capacity": 1,
      "id": "now",
      "period": 0
    },
    {
      "decision_capacity": 1,
      "id": "after-pilot",
      "period": 1
    }
  ],
  "decisions": [
    {
      "actions": [
        {
          "id": "commit",
          "value_scenarios": [
            30,
            -30
          ]
        },
        {
          "id": "hold",
          "value_scenarios": [
            5,
            5
          ]
        }
      ],
      "deadline_period": 1,
      "decision_effort": 1,
      "delay_cost_per_period": 10,
      "earliest_period": 0,
      "id": "platform-commitment"
    }
  ],
  "information_releases": [
    {
      "decision_id": "platform-commitment",
      "id": "pilot-signal",
      "period": 1,
      "signal_ids": [

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": [
    "Every scenario is a coherent joint future across decisions, action values share one governed unit and horizon, delay costs are complete and incremental, and information partitions contain only signals genuinely observable before the scheduled decision.",
    "Within each available signal state the policy chooses the highest conditional expected-value action; scenario labels are not leaked future outcomes, and the latest eligible release replaces rather than silently combines incompatible signal models.",
    "Decision effort represents scarce aggregate governance or analysis capacity, strict dependencies require predecessors in earlier periods, and all submitted decisions must be scheduled inside their governed windows; an infeasible result is an abstention requiring scope or capacity review.",
    "The calendar is optimal only for the declared common scenarios, values, delay costs, information releases, capacity, dependencies, and solver guarantee; it does not authorize automatic strategic, investment, employment, or safety decisions."
  ],
  "configuration": {
    "information_must_arrive_by_selected_period": true,
    "maximum_cvar_loss": null,
    "minimum_calendar_value": 0,
    "risk_aversion": 0,
    "strict_precedence": true,
    "tail_probability": 0.1
  },
  "decision": "information_aware_decision_calendar_selected",
  "decision_diagnostics": [
    {
      "available_signal_count": 2,
      "contingent_action_policy": [
        {
          "conditional_expected_value": 30,
          "selected_action_id": "commit",
          "signal_id": "high",
          "signal_probability": 0.5
        },
        {
          "conditional_expected_value": 5,
          "selected_action_id": "hold",
          "signal_id": "low",
          "signal_probability": 0.5
        }
      ],
      "deadline_period": 1,
      "decision_effort": 1,
      "decision_id": "platform-commitment",
      "delay_cost": 10,
      "earliest_period": 0,
      "expected_value_at_selected_period": 7.5,
      "incremental_value_vs_earliest_decision": 2.5,
      "latest_information_release_period": 1,
      "must_follow_ids": [],
      "selected_period": 1,
      "truncated_signal_policy_count": 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 coherent joint scenarios, feasible actions and values, decision windows, delay costs, strict dependencies, period capacity, and scenario-signal partitions whose release times precede any action they inform.
2. 2 At each eligible period, choose the best action conditional on the latest available signal partition and compute scenario value net of delay; then optimize the joint schedule under precedence and capacity by bounded exact enumeration or disclosed coordinate search.
3. 3 Return the chosen period and contingent action policy for every decision, information value versus deciding at the earliest date, capacity use, joint expected value and CVaR, and abstain if no complete feasible calendar exists.

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": "schedule dependent strategic decisions as information" }
  → finds "optimize_decision_calendar"

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

gitrevio_capability_run
  { "capability_id": "optimize_decision_calendar", "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 →