> For the complete documentation index, see [llms.txt](https://docs.zipwire.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zipwire.io/zipwire-collect/machine-vision/failure-to-recognise.md).

# Failure to Recognise

Upon upload, the AI will try to detect the kind of document and match it to an open collection.

When using either the [Bulk Upload](/zipwire-collect/bulk-upload.md) feature or when sending via WhatsApp, Zipwire Collect relies on just the AI to determine what a file or photo contains. If it fails to recognise the doc, then it defaults to a type "Unknown" and will not be matched to a collection.

### Give it a hint

When using the **Pick file** action for the item within a collection request on the **Open** tab, the AI will be told to expect a document of the type being asked for, like a hint.

If it cannot determine it from looking at the image and text, Zipwire assumes the user has, for example, picked a passport file for the passport item.

In other words, for tricky files, use the **Pick file** button on the collection itself.

[What the Respondent Sees at Their End](/zipwire-collect/what-the-respondent-sees-at-their-end.md)


---

# 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 dynamically by asking a question.

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

```
GET https://docs.zipwire.io/zipwire-collect/machine-vision/failure-to-recognise.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.