Appliance error codes are buried in PDFs and forum posts. Covala structures them as API data — error code, what it means, what causes it, and how to fix it.
Structured error codes by product type with descriptions, causes, and severity levels. No more parsing manufacturer PDFs.
Common failure modes per product type with symptoms, causes, and frequency data. Power diagnostic workflows.
Step-by-step repair instructions with difficulty ratings, estimated time, and tools needed. Build guided repair experiences.
{
"product_type": "Dishwashers",
"knowledge": [
{
"type": "error_codes",
"items": [
{
"code": "E1 / HE",
"meaning": "Water heating error",
"causes": [
"Faulty heating element",
"Thermistor failure"
],
"severity": "moderate"
},
{
"code": "E4 / OE",
"meaning": "Drain error",
"causes": [
"Clogged drain hose",
"Faulty drain pump"
],
"severity": "moderate"
}
]
},
{
"type": "failure_modes",
"items": [
{
"symptom": "Not cleaning dishes properly",
"causes": [
"Clogged spray arms",
"Low water pressure",
"Worn wash pump"
],
"frequency": "common"
}
]
}
]
}Repair data is scattered across manufacturer PDFs, support forums, and technician notes. Covala structures it so you don't have to.
Error code lookup gets users to your app. The rest of the data keeps them there.
Preventive maintenance data per product type — recommended intervals, tasks, and seasonal tips. Reduce failures before they happen.
Average lifespan, reliability ratings, and repair-vs-replace recommendations based on product age and repair cost.
When repair isn't worth it, show replacement costs from 20 retailers. Cross-retailer matching means one product, every price.
Feed diagnostic data directly to AI troubleshooting assistants. Request format=ai for condensed summaries optimized for LLM context windows.
Yes. Covala provides structured error codes per product type through a REST API. Each error code includes a human-readable meaning, a list of probable causes, and a severity level. You query by product type (e.g., dishwashers, washing machines) and get back clean JSON — no scraping, no PDF parsing.
Use Covala’s knowledge API. Request error codes, failure modes, and fix steps for any product type and get structured JSON you can render directly. Error codes include causes and severity. Failure modes include symptoms and frequency. Fix steps include difficulty ratings and estimated time.
Covala provides three types of repair data through its knowledge API: error codes with descriptions, causes, and severity levels; failure modes with symptoms, causes, and frequency data; and DIY fix steps with difficulty ratings, estimated time, and tools needed. Additional layers include maintenance schedules, lifespan data, and repair-vs-replace guidance.
Yes. Failure mode data includes symptoms, probable causes, and frequency ratings — the building blocks of a diagnostic decision tree. Combine that with error code lookups and fix steps to build a complete troubleshooting flow from symptom identification through resolution.
Error codes are organized by product type, not by individual brand. This means a query for dishwasher error codes returns patterns that apply across manufacturers — E1/HE for heating errors, E4/OE for drain errors, and so on. This is more useful for diagnostic apps because the same symptom often maps to the same root cause regardless of brand.
Cross-retailer pricing, already matched. Build comparison features without building matching infrastructure.
Give your agent structured product tools via MCP or REST. Specs, pricing, and knowledge — not web scraping.
Maintenance schedules, lifespan data, and replacement planning for every product type — structured as API data.
Error codes, failure modes, and fix steps — structured as API data for 620+ product types across 20 retailers.