Construct quality speed cost pareto surface

What it's for

Makes quality, speed, and cost tradeoffs visible under uncertainty instead of burying them in one stakeholder-weighted score.

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.

{
  "alternatives": [
    {
      "cost_scenarios": [
        100,
        110,
        120
      ],
      "delivery_time_scenarios": [
        5,
        6,
        7
      ],
      "id": "balanced",
      "quality_scenarios": [
        90,
        85,
        80
      ]
    },
    {
      "cost_scenarios": [
        180,
        180,
        190
      ],
      "delivery_time_scenarios": [
        8,
        8,
        9
      ],
      "id": "premium",
      "quality_scenarios": [
        98,
        95,
        90
      ]
    },
    {
      "cost_scenarios": [
        90,
        95,
        100
      ],

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.

{
  "alternative_diagnostics": [
    {
      "alternative_id": "balanced",
      "balanced_maximin_score": 0.4217,
      "eligible_frontier": true,
      "expected_cost": 111,
      "expected_delivery_time": 6.1,
      "expected_quality": 84.5,
      "frontier_membership_probability": 1
    },
    {
      "alternative_id": "fast",
      "balanced_maximin_score": 0,
      "eligible_frontier": true,
      "expected_cost": 95.5,
      "expected_delivery_time": 4.1,
      "expected_quality": 77.5,
      "frontier_membership_probability": 1
    },
    {
      "alternative_id": "premium",
      "balanced_maximin_score": 0,
      "eligible_frontier": true,
      "expected_cost": 183,
      "expected_delivery_time": 8.3,
      "expected_quality": 94.1,
      "frontier_membership_probability": 1
    }
  ],
  "assumptions": [
    "Alternatives are feasible, comparable, and evaluated on one quality definition, delivery horizon, cost perimeter, and aligned joint scenario set.",
    "Practical epsilons express material dominance; frontier probability is scenario-model membership, not a confidence interval or causal probability.",
    "The maximin navigator is a transparent weight-free compromise aid, not a universal winner; accountable owners must still choose preferences and constraints."
  ],
  "configuration": {
    "cost_epsilon": 0,
    "delivery_time_epsilon": 0,
    "minimum_frontier_probability": 0.5,
    "quality_epsilon": 0,
    "scenario_count": 3
  },
  "decision": "quality_speed_cost_frontier_available",
  "method": "stochastic_quality_speed_cost_pareto_surface_v1",

How it works

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

1. 1 Freeze feasible comparable alternatives, one quality definition, delivery horizon, fully loaded cost perimeter, aligned joint scenarios/probabilities, and practical objective epsilons.
2. 2 Apply three-objective dominance within every scenario, integrate each alternative's frontier membership probability, and retain options clearing the governed membership gate.
3. 3 Offer a normalized worst-objective maximin navigator as a transparent compromise aid while preserving the full frontier for accountable preference and constraint choice.

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": "construct a stochastic threedimensional quality deliverytime" }
  → finds "construct_quality_speed_cost_pareto_surface"

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

gitrevio_capability_run
  { "capability_id": "construct_quality_speed_cost_pareto_surface", "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 Finance & unit economics →