Audit commercial technical commitment integrity

What it's for

Shows when sales has promised technical scope that is orphaned, double-sold, dependency-impossible, unfunded or planned after the contractual date—before it becomes a customer and cash crisis.

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.

{
  "commitments": [
    {
      "acceptance_criteria_verified": true,
      "contract_evidence_verified": true,
      "contract_id": "contract-1",
      "contract_signed_period": 0,
      "contracted_scope_units": 10,
      "funded_capacity_units": 10,
      "id": "commitment-1",
      "maximum_contractual_penalty": 100,
      "promised_delivery_period": 10,
      "value_stream_id": "enterprise"
    }
  ],
  "scope_allocations": [
    {
      "allocation_fraction": 1,
      "commitment_id": "commitment-1",
      "dependency_scope_item_ids": [],
      "estimated_scope_units": 10,
      "id": "allocation-1",
      "planned_completion_period": 8,
      "planned_start_period": 1,
      "scope_evidence_verified": true,
      "scope_item_id": "scope-1"
    }
  ]
}

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.

{
  "commitment_diagnostics": [
    {
      "commitment_id": "commitment-1",
      "contract_id": "contract-1",
      "contracted_scope_gap": 0,
      "failed_checks": [],
      "funded_capacity_gap": 0,
      "latest_planned_completion_period": 8,
      "mapped_scope_units": 10,
      "maximum_contractual_penalty": 100,
      "promised_delivery_period": 10,
      "value_stream_id": "enterprise"
    }
  ],
  "configuration": {
    "maximum_absolute_reconciliation_error": 0.01,
    "maximum_relative_reconciliation_error": 0.001
  },
  "decision": "commercial_technical_commitments_supported",
  "guardrails": [
    "Technical scope evidence does not interpret legal obligations, acceptance rights, remedies, or revenue recognition.",
    "Shared scope is allocated explicitly; the same technical work cannot silently fund several contractual promises at full value.",
    "Contract, product, engineering, finance, customer-success, and legal owners must approve their respective facts."
  ],
  "method": "commercial_obligation_scope_allocation_dependency_capacity_integrity_audit",
  "summary": {
    "allocation_count": 1,
    "commitment_count": 1,
    "cyclic_scope_item_count": 0,
    "failed_commitment_count": 0,
    "maximum_contractual_penalty_exposed": 0,
    "overallocated_scope_item_count": 0,
    "scope_item_count": 1,
    "unknown_dependency_count": 0
  },
  "truncation": {
    "commitments_omitted": 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 signed commitment, promised date, acceptance criteria, contracted scope, funded capacity and maximum-penalty facts, then join technical scope only through governed commitment and scope-item identities.
2. 2 Reconcile fraction-weighted technical scope to each contracted amount and every shared scope item's total allocation to at most one, retaining unfunded scope and unverified evidence rather than netting gaps away.
3. 3 Audit dependency existence, acyclicity and planned temporal order, compare the latest technical completion with the promise, and return bounded commitment-level exposure diagnostics.

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 signed commercial promises against explicitly" }
  → finds "audit_commercial_technical_commitment_integrity"

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

gitrevio_capability_run
  { "capability_id": "audit_commercial_technical_commitment_integrity", "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 →