# Matching Confidence

The matcher is a foundational piece of technology that reconciles market, listing and data inputs describing cars against our vehicle catalogue. This is done so you can utilise our market-leading vehicle ID for additional workflows like valuation, market data and more. 

For example, when you request information on a registration plate the primary input we receive is its description "`upstream_vehicle": "2019 Isuzu Ute MU-X 4x2 LS-M 4 Wagon 6sp auto 3.0L 3000cc 4cyl T/Diesel 2018.` That needs to be matched to "id": "4843865643155456" which represents hundreds of data points related to the Isuzu.

We are transparent about the confidence of the match and you can leverage this to inform your workflows. In each relevant vehicle discovery method you will receive a "confidence" response. 

<table><thead><tr><th width="333">Confidence Parameter</th><th>Explanation</th></tr></thead><tbody><tr><td><p></p><pre class="language-json"><code class="lang-json">    "confidence": "standard",
</code></pre></td><td>The match from the input provided was at our standard confidence and is reliable for all use cases.</td></tr><tr><td><p></p><pre class="language-json"><code class="lang-json">    "confidence": "reduced",
</code></pre></td><td>The match from the input provided was not reliably matched and we have a lower confidence for its usage in general use cases. </td></tr></tbody></table>

In the reduced confidence outcome we highly recommend showing the `upstream_vehicle` parameter. This will help your user ensure the vehicle we have responded with is representative of the real vehicle.&#x20;


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://devhub.autotek.my/vehicle-search/matching-confidence.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.