Optimize discount policy

What it's for

Finds discounts that create contribution rather than vanity volume, while limiting margin tail loss, delivery overload and unjustified cross-segment dispersion.

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.

{
  "discount_options": [
    {
      "discount_rate": 0,
      "id": "growth-list",
      "incremental_retained_units_scenarios": [
        0,
        0
      ],
      "incremental_service_cost_scenarios": [
        0,
        0
      ],
      "purchase_probability_scenarios": [
        0.2,
        0.25
      ],
      "segment_id": "growth"
    },
    {
      "discount_rate": 0.1,
      "id": "growth-ten",
      "incremental_retained_units_scenarios": [
        1,
        2
      ],
      "incremental_service_cost_scenarios": [
        20,
        30
      ],
      "purchase_probability_scenarios": [
        0.25,
        0.35
      ],
      "segment_id": "growth"
    }
  ],
  "maximum_expected_discount_spend": 500,
  "maximum_expected_units": 50,
  "scenarios": [
    {
      "id": "base",
      "probability": 0.7
    },

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.

{
  "decision": "deploy_governed_aggregate_discount_policy",
  "failed_gates": [],
  "guardrails": [
    "Purchase, retention, and service-cost scenarios must come from randomized, quasi-experimental, or explicitly assumption-labeled evidence; observed correlation or a fitted elasticity is not automatically a causal discount response.",
    "Segments must be aggregate, commercially legitimate, prospectively defined, and reviewed for legal and ethical pricing constraints; protected traits, nationality, inferred vulnerability, or named-person behavior are prohibited.",
    "Maximum discount-gap, spend, capacity, contribution, and tail gates supplement rather than replace legal, tax, revenue-recognition, channel-conflict, brand, customer-trust, and approval controls.",
    "The selected policy is not authority to change prices, target individuals, discriminate, manipulate customers, or deploy an untested causal policy; heuristic mode has no global certificate."
  ],
  "method": "scenario_constrained_aggregate_discount_policy_v1",
  "scenario_diagnostics": [
    {
      "baseline_contribution": 1500,
      "delivered_units": 26,
      "discount_spend": 260,
      "policy_contribution": 1670,
      "probability": 0.7,
      "scenario_id": "base"
    },
    {
      "baseline_contribution": 1875,
      "delivered_units": 37,
      "discount_spend": 370,
      "policy_contribution": 2375,
      "probability": 0.3,
      "scenario_id": "upside"
    }
  ],
  "selected_policy": [
    {
      "discount_rate": 0.1,
      "option_id": "growth-ten",
      "segment_id": "growth"
    }
  ],
  "solver": {
    "evaluated_policy_count": 2,
    "global_optimality_certificate": true,
    "maximum_exact_states": 100000,
    "method": "exact_multiple_choice_enumeration",
    "nominal_policy_count": 2
  },
  "summary": {
    "cvar_contribution_loss_vs_baseline": 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 Define aggregate commercial segments, a unique zero-discount baseline and candidate rate for each segment, coherent purchase/retention/service-cost scenarios, contribution economics and operational constraints.
2. 2 Evaluate feasible multiple-choice policies, calculate scenario contribution, units and discount spend, and penalize CVaR contribution loss relative to the feasible baseline.
3. 3 Choose the risk-adjusted contribution-maximizing policy, apply contribution and tail gates, and return segment choices and adverse scenario diagnostics with solver certainty.

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": "optimize one aggregate discount option per" }
  → finds "optimize_discount_policy"

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

gitrevio_capability_run
  { "capability_id": "optimize_discount_policy", "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 Customer, revenue & pricing →