Optimize AI compliance control portfolio

What it's for

Finds the highest-value reusable AI compliance portfolio across products and jurisdictions while exposing tail loss, constraints, current-state uplift and the Pareto frontier.

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.

{
  "compliance_plans": [
    {
      "common_failure_detection_probability_scenarios": [
        0,
        0
      ],
      "control_ids": [
        "current-control"
      ],
      "deployment_delay_days_scenarios": [
        0,
        0
      ],
      "evidence_verified": true,
      "id": "high-risk-current",
      "is_current_state": true,
      "noncompliance_probability_scenarios": [
        0.2,
        0.4
      ],
      "obligation_class_id": "high-risk",
      "plan_operating_cost_scenarios": [
        0,
        0
      ],
      "remediation_success_probability_scenarios": [
        0,
        0
      ],
      "value_retention_fraction": 1
    },
    {
      "common_failure_detection_probability_scenarios": [
        0.9,
        0.7
      ],
      "control_ids": [
        "shared-assurance"
      ],
      "deployment_delay_days_scenarios": [
        0,
        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.

{
  "assumptions": [
    "Plan noncompliance and remediation probabilities are prospectively validated at aggregate obligation-class grain; counsel supplies obligation/control admissibility; shared controls, common jurisdiction states and unique value are represented once.",
    "All executable plans, control dependencies/exclusions, full costs, delay, capacity, budget and finance losses are complete on one horizon and currency basis."
  ],
  "baseline_current_state": {
    "expected_net_value": 587270,
    "expected_total_loss": 393630,
    "loss_conditional_value_at_risk": 2674000,
    "selected_control_ids": [
      "current-control"
    ],
    "selected_plan_ids": [
      "high-risk-current",
      "transparency-current"
    ]
  },
  "decision": "implement_selected_ai_compliance_control_portfolio",
  "economics": {
    "expected_common_jurisdiction_loss": 5500,
    "expected_direct_noncompliance_loss": 34660,
    "expected_net_value": 828830,
    "expected_operating_cost": 11910,
    "expected_retained_business_value": 980900,
    "expected_total_loss": 40160,
    "implementation_cost": 100000,
    "loss_conditional_value_at_risk": 490000,
    "loss_value_at_risk": 340000,
    "risk_adjusted_score": 706330,
    "tail_probability": 0.05
  },
  "limitations": [
    "The optimizer ranks a submitted internal planning model; it is not legal advice, regulatory interpretation, conformity certification, procurement authority or permission to deploy.",
    "Results concern aggregate systems and obligations, never legal fault, intent, misconduct, nationality, loyalty or employment suitability of a person."
  ],
  "method": "shared_control_beta_binomial_ai_compliance_cvar_portfolio_v1",
  "obligation_diagnostics": [
    {
      "expected_residual_noncompliant_systems": 0.1415,
      "noncompliance_probability_by_scenario": [
        0.0748,
        0.3351
      ],
      "obligation_class_id": "high-risk",

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 Simulate obligation-class noncompliance from governed Beta priors and coherent scenarios, then apply prospectively validated plan ceilings, remediation, delay, operating cost and retained value.
2. 2 Union shared controls across plans so implementation cost, operating cost and capacity count once; enforce required controls, evidence, dependencies, exclusions, budget and risk limits as hard gates.
3. 3 Count common jurisdiction value once through joint detection survival, then maximize expected net value minus loss CVaR by exact enumeration or a disclosed deterministic beam and expose nondominated portfolios.

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 reusable ai compliance controls and" }
  → finds "optimize_ai_compliance_control_portfolio"

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

gitrevio_capability_run
  { "capability_id": "optimize_ai_compliance_control_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 AI risk, rights & assurance →