# Image reading

### Can the AI agent see images?

Yes, our AI customer service agents can see images that are shared either in chats, email bodies or as attachments to emails.

It will process the image, and use it as context when answering the user or customer's question.

### Which helpdesks is image reading available for?

Image reading is currently available for the following helpdesks and channels:

<table><thead><tr><th width="226.58984375">Helpdesk/channel</th><th width="203.30078125">Available?</th></tr></thead><tbody><tr><td>Intercom chat</td><td>Yes</td></tr><tr><td>Intercom email</td><td>Yes</td></tr><tr><td>Zendesk Messaging</td><td>Yes</td></tr><tr><td>Zendesk Tickets/Forms</td><td>Yes</td></tr><tr><td>Freshdesk</td><td>Yes</td></tr><tr><td>Freshchat</td><td>Coming soon</td></tr><tr><td>Gorgias chat</td><td>Coming soon</td></tr><tr><td>Gorgias email</td><td>Coming soon</td></tr><tr><td>HubSpot chat</td><td>Coming soon</td></tr><tr><td>HubSpot email</td><td>Coming soon</td></tr><tr><td>Slack</td><td>No</td></tr><tr><td>Teams</td><td>No</td></tr><tr><td>API</td><td>No</td></tr></tbody></table>

### How much does image reading cost?

You only pay $0.02 per reply where image reading is used.

### &#x20;How many images does it read in a message?

Up to 3 images can be 'read' and processed in a message or reply.

### Can images be used in tasks?

Yes, you can refer to images within tasks e.g. "Request an image from the user of the damaged parcel" or "when the user shares an image, transfer the conversation".

### Can images be used in guidance?

Yes, guidance can refer to images e.g. "If someone shares an image of a broken box, escalate the conversation".

### Will I see images in Inspect & Logs?

The images themselves are not stored on our servers and so we can't share them in your logs.&#x20;

However, we do share the description of the image so you can refer back to it when reviewing a ticket.


---

# 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://support.myaskai.com/features/image-reading.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.