Overview

AUTO-REPR-070, Evaluate Mobile Service Feasibility, ranks candidate mobile repair or maintenance service models by market demand, startup cost, margin potential, technician availability, service scope fit, and operational risk.

Decision ID

AUTO-REPR-070

Decision Name

Evaluate Mobile Service Feasibility

Industry Profile

auto-repair-evaluate-mobile-service-feasib-auto-repr-070 version 1.0.0

Default Profile

balanced

Default Scenario

standard

Catalog

DKR-AUTO-RUNTIME-001, active DKS runtime catalog

Understanding This Decision

Evaluate Mobile Service Feasibility helps an auto repair business compare possible mobile service models before investing in vehicles, technicians, scheduling capacity, and operating processes.

Architecture

1. Request a token from the Identity service.
2. Use the returned jwtToken as the bearer token.
3. Load the catalog and decision detail from DKS.
4. Build a Prepared Decision Input using canonical criterion IDs.
5. Execute the decision through DDE.
6. Use X-Request-Id and X-Correlation-Id for tracing across DDE and DKS.

Authentication

Request a secure session token from Identity. The current token response field is jwtToken.

POST https://identity.vinquery.com/connect/token
Content-Type: application/json

{
  "clientId": "{clientId}",
  "clientSecret": "{clientSecret}",
  "audience": "vinquery:api:decisioq"
}

Catalog Discovery

Use DKS to discover the catalog and then load complete metadata for AUTO-REPR-070.

GET https://dks.vinquery.com/decisioncatalog
Authorization: Bearer {jwtToken}

GET https://dks.vinquery.com/decisioncatalog/decisions/AUTO-REPR-070
Authorization: Bearer {jwtToken}

Criteria

Criterion IDs are intentionally stable machine identifiers. Display labels are for users; request values should be keyed by canonical criterionId.

Constraint Processing

This decision includes a catalog-defined hard constraint. DKS returns the constraint with the decision detail, and DDE evaluates it before criteria-based ranking.

{
  "constraintSummary": {
    "definedConstraintCount": 1,
    "activeConstraintCount": 1,
    "eligibleOptionCount": 2,
    "excludedOptionCount": 1,
    "eligibleOptions": [
      "option-1",
      "option-2"
    ],
    "excludedOptions": [
      {
        "optionId": "option-3",
        "reasons": [
          "Operational risk score is above the maximum threshold of 40."
        ]
      }
    ]
  }
}

const constraints = decisionDetail.constraints || [];
if (constraints.length > 0) {
  // DDE applies catalog constraints before ranking.
  // Excluded candidates appear in response.constraintSummary.excludedOptions.
}

const summary = response.constraintSummary;
const excluded = response.decisionResult?.excludedOptions || [];

Excluded candidates do not participate in ranking because hard constraints are evaluated before scoring. For AUTO-REPR-070, option-3 is excluded from the showcase sample because its operational risk score is above the catalog threshold.

Industry Profile

The active industry profile uses $.repairOrders as the options path, $.optionId as the option ID, and $.name as the option display name.

{
  "repairOrders": [
    {
      "optionId": "option-1",
      "name": "Mobile Battery Replacement",
      "assessment": {
        "marketDemandScore": 88,
        "marginPotentialScore": 88,
        "technicianAvailabilityScore": 88
      },
      "financial": {
        "startupCost": 450
      },
      "business": {
        "performance": {
          "serviceScopeFit": 88
        }
      },
      "risk": {
        "operationalRiskScore": 20
      }
    }
  ]
}

{
  "optionId": "option-1",
  "name": "Mobile Battery Replacement",
  "values": {
    "market_demand_score": 88,
    "startup_cost": 450,
    "margin_potential_score": 88,
    "technician_availability_score": 88,
    "service_scope_fit": 88,
    "operational_risk_score": 20
  }
}

Profiles and Scenarios

A profile changes criterion weights. A scenario describes the operating context for the execution. The active DKS catalog exposes these choices with the decision detail response.

Prepared Input

For Prepared Decision Input, send decisionId, selected profile/scenario IDs, and option values keyed by canonical criterion ID. The showcase request includes two eligible mobile service models and one excluded model so constraint handling is visible.

{
  "decisionId": "AUTO-REPR-070",
  "mappingProfileId": "auto-repair-evaluate-mobile-service-feasib-auto-repr-070",
  "mappingProfileVersion": "1.0.0",
  "profileId": "balanced",
  "scenarioId": "standard",
  "algorithm": "TOPSIS",
  "weightStrategy": "Manual",
  "runSensitivity": false,
  "requestContext": {
    "correlationId": "auto-repr-070-demo-001"
  },
  "options": [
    {
      "optionId": "option-1",
      "name": "Mobile Battery Replacement",
      "values": {
        "market_demand_score": 88,
        "startup_cost": 450,
        "margin_potential_score": 88,
        "technician_availability_score": 88,
        "service_scope_fit": 88,
        "operational_risk_score": 20
      }
    },
    {
      "optionId": "option-2",
      "name": "Mobile Tire Service",
      "values": {
        "market_demand_score": 81,
        "startup_cost": 750,
        "margin_potential_score": 81,
        "technician_availability_score": 81,
        "service_scope_fit": 81,
        "operational_risk_score": 35
      }
    },
    {
      "optionId": "option-3",
      "name": "Mobile Maintenance Van",
      "values": {
        "market_demand_score": 74,
        "startup_cost": 1100,
        "margin_potential_score": 74,
        "technician_availability_score": 74,
        "service_scope_fit": 74,
        "operational_risk_score": 50
      }
    }
  ]
}

Execute

curl -X POST "https://dde.vinquery.com/api/v1/decide" \
  -H "Authorization: Bearer ${DECISIOQ_TOKEN}" \
  -H "Content-Type: application/json" \
  -H "X-Correlation-Id: auto-repr-070-demo-001" \
  --data @auto-repr-070-execute.json

DDE retrieves authoritative criteria, constraints, and validation metadata from DKS, executes the deterministic ranking, and returns the decision result plus execution metadata.

Interpret the Result

The successful response is centered on decisionResult. The winner and ranking are deterministic outputs; optional explanation fields add context but do not change the ranking.

{
  "success": true,
  "decisionType": "AUTO-REPR-070",
  "decisionResult": {
    "winner": "option-1",
    "ranking": [
      {
        "optionId": "option-1",
        "name": "Mobile Battery Replacement",
        "score": 0.91
      },
      {
        "optionId": "option-2",
        "name": "Mobile Tire Service",
        "score": 0.84
      }
    ],
    "excludedOptions": [
      {
        "optionId": "option-3",
        "reasons": [
          "Operational risk score is above the maximum threshold of 40."
        ]
      }
    ]
  },
  "constraintSummary": {
    "definedConstraintCount": 1,
    "activeConstraintCount": 1,
    "eligibleOptionCount": 2,
    "excludedOptionCount": 1
  },
  "requestContext": {
    "correlationId": "auto-repr-070-demo-001"
  }
}

Sensitivity Analysis

Set runSensitivity to true on catalog execution when the client wants recommendation-stability information in the same response. The sensitivity engine perturbs criterion weights by controlled factors and reports whether the winner remains stable.

{
  "sensitivityResult": {
    "stableWinner": true,
    "winner": "option-1",
    "mostSensitiveCriterion": "startup_cost",
    "confidence": 95,
    "criterionImpacts": {
      "startup_cost": 0.1842
    },
    "winnerChangeCounts": {
      "startup_cost": 0
    }
  }
}

Use sensitivity output to decide whether a recommendation is robust enough for automation or should be reviewed by a person.

Explanation of Decision Result

Every successful response can include deterministic explanation text under decisionResult.explanation and explanation. If the optional AI layer is enabled, the response may also include an ai block with structured business-language explanation fields.

{
  "ai": {
    "enabled": true,
    "generated": true,
    "schemaValidated": true,
    "explanation": {
      "summary": "The selected mobile service model provided the strongest overall fit.",
      "whyRecommended": "It combined strong availability and quality with acceptable cost.",
      "keyDrivers": [],
      "tradeoffs": [],
      "competitors": [],
      "sensitivitySummary": "Sensitivity analysis was not included in this response.",
      "scenarioSummary": "The standard scenario was selected.",
      "risks": [],
      "nextSteps": [],
      "assumptions": []
    }
  }
}

Tracing and Logs

Use request identifiers to connect client, catalog, and execution activity during support or integration testing.

X-Request-Id

Optional client-supplied request ID. If omitted, the server generates one.

X-Correlation-Id

Optional client correlation value propagated from DDE to DKS.

requestContext.correlationId

Optional payload value echoed in the response and used for tracing.

executionTrace

Advanced execution metadata including selected profile, selected scenario, effective weights, and applied constraints.

Code Examples

These examples demonstrate the current DecisioQ flow:

1. Request jwtToken from https://identity.vinquery.com/connect/token.
2. Load AUTO-REPR-070 metadata from https://dks.vinquery.com/decisioncatalog/decisions/AUTO-REPR-070.
3. Execute a Prepared Decision Input at https://dde.vinquery.com/api/v1/decide.

Set these environment variables before running any companion example:

DECISIOQ_CLIENT_ID
DECISIOQ_CLIENT_SECRET
DECISIOQ_AUDIENCE=vinquery:api:decisioq

Optional:
DECISIOQ_IDENTITY_URL=https://identity.vinquery.com/connect/token
DECISIOQ_DKS_URL=https://dks.vinquery.com
DECISIOQ_DDE_URL=https://dde.vinquery.com

Download the source files directly:

Troubleshooting

Production Checklist