Audit budget constraint binding

What it's for

Tests whether ‘we have no budget’ is the real constraint—or whether the current portfolio can create more value through a dependency-valid reallocation first.

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.

{
  "budget": 500000,
  "budget_increment": 300000,
  "initiatives": [
    {
      "cost": 500000,
      "current_selected": true,
      "dependency_ids": [],
      "id": "legacy-retention",
      "net_value_scenarios": [
        300000,
        550000,
        700000
      ]
    },
    {
      "cost": 500000,
      "current_selected": false,
      "dependency_ids": [],
      "id": "growth-engine",
      "net_value_scenarios": [
        400000,
        800000,
        1200000
      ]
    },
    {
      "cost": 300000,
      "current_selected": false,
      "dependency_ids": [
        "growth-engine"
      ],
      "id": "enterprise-layer",
      "net_value_scenarios": [
        -100000,
        300000,
        900000
      ]
    }
  ],
  "risk_aversion": 0.5,
  "scenario_probabilities": [
    0.2,
    0.5,

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": [
    "Initiative costs consume one governed budget horizon; aligned net-value scenarios already include all incremental economic costs and opportunity costs, so constrained cash is not subtracted again from value.",
    "Dependencies are complete and acyclic, initiatives are indivisible, scenario columns describe the same joint future, and omitted capacity, exclusivity, tax, financing, or strategic constraints can change whether budget appears binding.",
    "A positive reallocation gain diagnoses current-plan inefficiency separately from budget scarcity; only exact mode certifies the represented subset optimum, while heuristic mode has no global optimality certificate.",
    "Git activity cannot supply governed costs or business value by itself, and this portfolio audit must not be used for person-level performance or employment decisions."
  ],
  "configuration": {
    "budget": 500000,
    "budget_increment": 300000,
    "initiative_count": 3,
    "maximum_exact_states": 262144,
    "represented_state_count": 8,
    "risk_aversion": 0.5,
    "scenario_count": 3,
    "solver_mode": "exact_enumeration",
    "state_count_is_capped": false,
    "tail_probability": 0.1
  },
  "decision": "budget_constraint_genuinely_binding",
  "initiative_diagnostics": [
    {
      "constrained_selected": true,
      "cost": 500000,
      "current_selected": false,
      "dependency_ids": [],
      "expected_net_value": 840000,
      "initiative_id": "growth-engine",
      "selection_changed_by_reallocation": true,
      "standalone_risk_adjusted_value": 1040000,
      "unconstrained_selected": true
    },
    {
      "constrained_selected": false,
      "cost": 500000,
      "current_selected": true,
      "dependency_ids": [],
      "expected_net_value": 545000,
      "initiative_id": "legacy-retention",
      "selection_changed_by_reallocation": true,
      "standalone_risk_adjusted_value": 695000,
      "unconstrained_selected": true
    },
    {

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 current selected portfolio, indivisible initiative costs, complete dependency DAG, aligned net-value scenarios, budget, and one decision-sized budget increment.
2. 2 Re-optimize at the current budget, the incremented budget, and without the budget while preserving dependencies; score each portfolio by expected net value minus the governed CVaR-loss penalty.
3. 3 Call budget genuinely binding only when the unconstrained dependency-feasible solution costs more and creates materially more modeled value; report current-plan infeasibility and reallocation gain separately.

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 whether a claimed budget constraint" }
  → finds "audit_budget_constraint_binding"

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

gitrevio_capability_run
  { "capability_id": "audit_budget_constraint_binding", "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 →