Optimize commercial commitment portfolio

What it's for

Lets leadership choose which promises and terms the company can afford to make after delivery capacity, penalty exposure, liquidity and relationship value are considered together.

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.

{
  "capacity_by_period": [
    10,
    10,
    10
  ],
  "commercial_opportunities": [
    {
      "evidence_verified": true,
      "id": "opportunity-1"
    }
  ],
  "current_unrestricted_cash": 100,
  "delivery_budget": 100,
  "minimum_unrestricted_cash": 0,
  "scenarios": [
    {
      "evidence_verified": true,
      "fixed_cash_flow_by_period": [
        0,
        0,
        0
      ],
      "id": "base",
      "probability": 0.7
    },
    {
      "evidence_verified": true,
      "fixed_cash_flow_by_period": [
        -1,
        -1,
        -1
      ],
      "id": "stress",
      "probability": 0.3
    }
  ],
  "term_options": [
    {
      "capacity_units_by_period": [
        1,
        1,
        0
      ],

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.

{
  "capacity": {
    "available_by_period": [
      10,
      10,
      10
    ],
    "used_by_period": [
      1,
      1,
      0
    ]
  },
  "constraints": {
    "failed": [],
    "feasible_policy_found": true
  },
  "decision": "commercial_commitment_portfolio_supported",
  "guardrails": [
    "Options must be executable legal/commercial packages reviewed by accountable owners; the engine does not draft or accept contracts.",
    "Delivery scenarios and costs must be prospective and point-in-time; hindsight outcomes or LLM-invented estimates are prohibited.",
    "Declining an opportunity is always explicit, and no customer or worker is scored at person level.",
    "Only exact enumeration certifies the global optimum over supplied packages; beam output remains uncertified."
  ],
  "method": "commercial_multiple_choice_capacity_liquidity_cvar_term_portfolio",
  "scenario_diagnostics": [
    {
      "acceptance_cash": 100,
      "contractual_penalty": 0,
      "minimum_unrestricted_cash": 100,
      "probability": 0.7,
      "scenario_id": "base",
      "terminal_net_value": 126
    },
    {
      "acceptance_cash": 0,
      "contractual_penalty": 20,
      "minimum_unrestricted_cash": 78,
      "probability": 0.3,
      "scenario_id": "stress",
      "terminal_net_value": -19
    }
  ],
  "search": {

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 each opportunity and its legally/commercially executable term options, with promised date, deposit, acceptance cash, penalty schedule, capacity path and point-in-time scenario-specific delivery period, cost and relationship value.
2. 2 Precompute option/scenario cash, cost, penalty, acceptance and relationship outcomes; combine one decline-or-option choice per opportunity while charging shared fixed cash once and enforcing capacity in every period.
3. 3 Filter on budget, expected penalty, liquidity, acceptance-cash and CVaR gates, maximize expected terminal net value minus tail-risk penalty, and disclose exact enumeration or deterministic beam search without a false certificate.

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": "select decline or one executable contractterm" }
  → finds "optimize_commercial_commitment_portfolio"

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

gitrevio_capability_run
  { "capability_id": "optimize_commercial_commitment_portfolio", "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 →