> For the complete documentation index, see [llms.txt](https://devhub.autograb.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://devhub.autograb.com/nz-autograb-api-doc/vehicle-search/matching-confidence.md). # Matching Confidence Understand how we match vehicles and the expected outcomes. 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.
Confidence ParameterExplanation

    "confidence": "standard",
The match from the input provided was at our standard confidence and is reliable for all use cases.

    "confidence": "reduced",
The match from the input provided was not reliably matched and we have a lower confidence for its usage in general use cases.
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. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://devhub.autograb.com/nz-autograb-api-doc/vehicle-search/matching-confidence.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.