Send a Prompt and an Image to Get an Answer (Jestor AI)

When to Use

• Automatically extract data from invoices, receipts, or documents uploaded as images
• Classify or describe the content of an image stored in a file or image field
• Generate a text summary or analysis based on a photo attached to a record
• Combine visual input with a written instruction to produce structured or formatted output

How to Configure

Step 1 — Create a new automation

This page covers only the Send a Prompt and an Image to Get an Answer (Jestor AI) action. For instructions on how to access automations and create a new automation, see the Automations page.

Step 2 — Add the Jestor AI action

Under Do, click + Add action. In the search bar, type send a prompt and an image jestor and select Send a prompt and an image to get an answer.

Step 3 — Choose tab

In the Choose tab dropdown, select the table whose record you want to update with the AI response. This is usually the same table where the automation lives.

Step 4 — ID of your record

In the ID of your record field, select the field that holds the record's ID. This tells Jestor which record to write the response to.

Step 5 — Choose the field where the answer will be saved

Select the field in your table where Jestor AI's response will be stored. This field must already exist in the table — the automation will not create it automatically. Use a Long Text field for most use cases.

Step 6 — Image

Select a field from your record that contains the image or file you want to send to Jestor AI. It must be the content of an image field or a file field in Jestor. If it is a file field, the first file in the field will always be used.

Step 7 — Write prompt

Write the prompt you want to send alongside the image. You can reference field values from the current record using dynamic variables. Be specific — the quality of the prompt directly affects the quality of the response.

Step 8 (optional) — Max output tokens

Set a limit on the length of the response. If left empty, the model will use its default limit.

Step 9 — Save

Click Save to finalize the action, then Create to activate the automation.

Keep in Mind

• This action does not require an external AI connection — it runs entirely through Jestor AI, no OpenAI or Google account needed.
• This action does not create records — it only updates an existing field in an existing record. If you need to create a record with the response, combine this with a Create record action.
• This action does not support multi-turn conversations — it sends one prompt with one image and receives one response. There is no memory of previous runs.
• This action does not return structured data automatically — if you need JSON or a specific format, instruct the model in your prompt and parse the output separately.
• If the image field contains multiple files, only the first file is processed — the remaining files are ignored.
• The response is saved directly to the field — there is no preview or approval step before the content is written.

FAQ

1 — Do I need to connect an external AI account to use this action?

No. Unlike the ChatGPT version, this action uses Jestor's native AI. No OpenAI or Google account is required.

2 — Can I send multiple images in a single automation run?

No. This action processes one image per run. If the file field contains multiple files, only the first one will be used.

3 — What is the difference between this action and the ChatGPT image action?

Both actions analyze an image using AI and save the response to a field. The difference is the AI provider: this action uses Jestor AI natively, while the ChatGPT version requires an OpenAI connection. Use this one when you want to avoid managing external API credentials.

4 — Can I use dynamic field values inside the prompt?

Yes. You can reference field values from the triggering record inside the prompt — for example, including a record's name or category as part of the instruction sent alongside the image.

5 — What field type should I use to store the response?

Use a Long Text field for most cases. Short Text fields may truncate the response if the output exceeds the character limit.