Calculate procurement negotiation range

What it's for

Turns procurement leverage into a defensible, risk-gated price corridor while clearly separating observed buyer economics from uncertain counterparty assumptions.

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.

{
  "buyer_confidence_level": 0.6,
  "minimum_probability_positive_bargaining_zone": 0.6,
  "scenarios": [
    {
      "buyer_batna_total_cost": 120,
      "buyer_incremental_contract_value": 30,
      "buyer_transition_cost": 10,
      "id": "base",
      "probability": 0.6,
      "supplier_batna_profit": 20,
      "supplier_incremental_delivery_cost": 70,
      "supplier_risk_cost": 5
    },
    {
      "buyer_batna_total_cost": 105,
      "buyer_incremental_contract_value": 20,
      "buyer_transition_cost": 15,
      "id": "stress",
      "probability": 0.4,
      "supplier_batna_profit": 22,
      "supplier_incremental_delivery_cost": 78,
      "supplier_risk_cost": 8
    }
  ],
  "supplier_confidence_level": 0.6
}

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.

{
  "configuration": {
    "buyer_bargaining_weight": 0.5,
    "buyer_confidence_level": 0.6,
    "supplier_confidence_level": 0.6,
    "tail_probability": 0.1
  },
  "decision": "confidence_protected_negotiation_range_supported",
  "failed_gates": [],
  "guardrails": [
    "Buyer and supplier reservation economics must be independently sourced and scenario-aligned; a guessed supplier cost or private BATNA is not evidence and should trigger abstention upstream.",
    "The confidence-protected interval is deliberately conservative and can be empty even when the expected interval overlaps; an empty range means renegotiate scope, terms, evidence, or BATNA rather than manufacture a price.",
    "The target implements the submitted bargaining weight inside the supported range; it is not a prediction of acceptance, legal fairness, market price, or authority to negotiate, threaten, sign, renew, or terminate.",
    "Scenario tail loss and negotiation leverage describe aggregate contract economics, never vendor integrity, country risk by identity, or employee performance."
  ],
  "method": "uncertain_batna_confidence_protected_negotiation_range_v1",
  "scenario_diagnostics": [
    {
      "bargaining_surplus": 2,
      "buyer_reservation_price": 110,
      "probability": 0.4,
      "scenario_id": "stress",
      "supplier_reservation_price": 108,
      "target_buyer_overpayment": 0,
      "target_supplier_shortfall": 5.5
    },
    {
      "bargaining_surplus": 45,
      "buyer_reservation_price": 140,
      "probability": 0.6,
      "scenario_id": "base",
      "supplier_reservation_price": 95,
      "target_buyer_overpayment": 0,
      "target_supplier_shortfall": 0
    }
  ],
  "summary": {
    "buyer_cvar_overpayment_at_target": 0,
    "confidence_protected_buyer_ceiling": 110,
    "confidence_protected_supplier_floor": 95,
    "confidence_protected_zone_exists": true,
    "expected_bargaining_surplus": 27.8,
    "expected_buyer_reservation_price": 128,
    "expected_supplier_reservation_price": 100.2,

How it works

Decision analysis — Turn uncertainty, cost and risk appetite into a defensible choice, with the reasoning left inspectable.

1. 1 Build coherent scenarios for the buyer's outside-option cost, incremental contract value and transition cost, and for the supplier's incremental delivery cost, outside-option profit and risk cost.
2. 2 Derive scenario reservation prices, probability of a positive bargaining zone, confidence-protected floor and ceiling, and a bargaining-weight target without pretending private counterparty information is observed.
3. 3 Measure buyer overpayment and supplier shortfall tails at the target and apply governed overlap, confidence and CVaR gates before returning a usable range.

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": "calculate an uncertaintyaware procurement bargaining zone" }
  → finds "calculate_procurement_negotiation_range"

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

gitrevio_capability_run
  { "capability_id": "calculate_procurement_negotiation_range", "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 →