Available · v1

Warranty Intelligence

Send a customer's warranty claim with your warranty terms and purchase details. Get back the claim type, a coverage status, what information is missing, and the next workflow step.

  • Warranty periods computed exactly from your dates
  • Claims tested against each covered item and exclusion you supply
  • Likely exclusions go to review, never auto-denied
  • Safety concerns raised to high priority
Try it in the playgroundAPI reference
Request body
{
  "claim_description": "The left hinge on my laptop cracked while opening the lid normally. It was never dropped. Now the screen wobbles.",
  "product": {
    "name": "Example 14-inch Laptop",
    "model_number": "EX-14"
  },
  "purchase_date": "2025-06-12",
  "claim_date": "2026-03-02",
  "warranty_terms": {
    "coverage_months": 24,
    "covered": [
      "Defects in materials and workmanship under normal use"
    ],
    "exclusions": [
      "Damage caused by drops, impacts, or liquid",
      "Normal wear and tear, including cosmetic wear"
    ],
    "requires_proof_of_purchase": true
  },
  "proof_of_purchase": {
    "provided": true,
    "type": "receipt"
  }
}
Response · 200 OK
{
  "request_id": "req_Bv6kN1pRm8TzQ4wE",
  "claim_type": "manufacturing_defect",
  "coverage_status": "covered",
  "priority": "medium",
  "recommended_action": "process_claim",
  "requires_human_review": false,
  "required_information": [],
  "signals": [
    "within_warranty_period"
  ],
  "matched_terms": [
    {
      "term": "Defects in materials and workmanship under normal use",
      "kind": "covered",
      "evidence": "warranty_terms.covered[0]"
    }
  ]
}
The problem

Warranty intake is slow and inconsistent

Claims arrive as free text with missing dates and receipts. Agents re-read terms for every claim, and accidental damage, wear, and genuine defects get handled differently each time.

Claim classification
Manufacturing defect, premature failure, accidental damage, wear and tear, missing components, performance issue, or other.
Coverage evaluation
Period and proof of purchase in code; covered items and exclusions interpreted one at a time and quoted back.
Next steps
Process, troubleshoot, request information, review, or inform the customer it's outside the warranty period.
Use cases

Where teams use it

  • Warranty claim intake
  • Service desks
  • Manufacturer support
  • Retail extended warranties
  • Field service
Integrate

One HTTP call

const response = await fetch("https://kovca.io/api/v1/warranty/triage", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.KOVCA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "claim_description": "The left hinge on my laptop cracked while opening the lid normally. It was never dropped. Now the screen wobbles.",
    "product": {
      "name": "Example 14-inch Laptop",
      "model_number": "EX-14"
    },
    "purchase_date": "2025-06-12",
    "claim_date": "2026-03-02",
    "warranty_terms": {
      "coverage_months": 24,
      "covered": [
        "Defects in materials and workmanship under normal use"
      ],
      "exclusions": [
        "Damage caused by drops, impacts, or liquid",
        "Normal wear and tear, including cosmetic wear"
      ],
      "requires_proof_of_purchase": true
    },
    "proof_of_purchase": {
      "provided": true,
      "type": "receipt"
    }
  }),
});

if (!response.ok) {
  const { error, request_id } = await response.json();
  throw new Error(`${error.code}: ${error.message} (${request_id})`);
}

const { claim_type, coverage_status, recommended_action } = await response.json();

Related APIs

  • Returns Intelligence

    Classify return requests, check them against your return policy, and get a suggested next step.

  • Catalog Matching

    Decide whether two product records are the same item, a different variant, or a different product.

  • Compatibility Intelligence

    Determine whether two products work together using structured specifications, compatibility rules, and intelligent evaluation.

  • Listing Intelligence

    Check product listings for contradictions, missing attributes, unsupported claims, and your listing requirements before publication.