AI Block

This article explains the Get Data from AI block that can be used to design an app. This block can analyse both typed input and uploaded files from your app using field variables. For example, it can review text entered by users, interpret images uploaded through the Camera, image & files block, or read PDF documents, all based on the instructions you provide.

‍Use Case Examples

1. Quality assurance
2. Cleanliness audits
3. Safety gear analysis
4. Inventory identification without scanning codes
5. Crop Health Detector

Help Video

Editing the Block

Click on the block and start editing on the panel that appears on the right side.

‍

Label

This is what appears as the label for the dropdown that shows the list of the items from the master app. Usually people provide labels such as "Display the item", "Calculate total score", etc.

Select LLM

Select the AI provider you want to use. Currently available options include OpenAI, Claude, and Gemini.

Each provider has its own strengths, and you may need to experiment with different ones to get the output that best suits your use case.

AI Model

Once an LLM is selected, this dropdown shows the corresponding list of available models. Choose a model from the list to power your AI interaction. The different models available allow you to experiment and find the one that provides the most accurate or relevant responses for your task.

Note: The output may vary slightly depending on the model chosen, even if the instructions are the same. If needed, test your instructions on the provider’s platform before using them in the app to reduce unnecessary AI calls.

Description

Description is positioned below the Input block which explains to the end user about the data that will be generated once they click on the AI button.

Description is positioned below the Input block which explains to the end user about the data that will be generated once they click on the Get Data from AI.

Description is an optional field.‍

NOTE - Since the Get Data from AI block is an Auto-Generated feature, it doesn’t require the user to enter any data into the block.

Instructions

Configure the AI block by typing in the exact instructions to display the data that is needed.

For example, to fetch data from external sites, detect and display details in uploaded images or even perform calculations on uploaded files and images. 

You can also use field variable names to make the AI analyse inputs from different app fields present.

Note: Tweak your instructions to get the required results before distributing the app to users.

File Handling

The AI block can also process uploaded files such as PDFs and images.

PDF documents or images can be analysed for information extraction, summaries, or other tasks.

Note: When using Claude, the AI block can process up to 100 pages in a PDF document. Only document-type files are supported currently. Once additional formats are supported by the underlying models, they may be available here as well.

Example 1: To calculate the total score in a checklist uploaded using the Camera, Images & Files block.

Blocks used: Camera, Images & Files block, Get Data from AI block.

Instructions: Check the scores in {upload_sc} under the score coloumn and calculate the total score. Display only the final value out of 100.

LLM: OpenAI

AI Model: gpt-4o

‍

‍

Example 2: Detect cleanliness of a room.

Blocks used: Camera, Images & Files block, Get Data from AI block.

Instructions: Check if the room in {upload_ima} is clean or not. Display only yes or no.

LLM: OpenAI

AI Model: gpt-4o

‍

‍

Example 3: Detect the distance traveled by a vehicle by checking the odometer.

In cases where the value is in between changing to the next increment, some OCR may not be able to detect it accurately. But the Get data from AI will be able to detect it accurately.

Blocks used: Camera, Images & Files block, Get Data from AI block.

Instructions: In {upload_ima}, check the trip distance traveled in the odometer and only display the distance. If it is about to change, display that distance instead.

LLM: OpenAI

AI Model: gpt-4o

‍

Here, the distance, in the image, is about to change from 144.2km to 144.3km .

‍

Required

Enable this option to tell the user that it is a compulsory field. Without generating the output of this block, users will not be able to make a submission if enabled.

Advanced Options

Advanced Label

The Advanced Label option allows you to change the label of a field dynamically based on a condition you define. Instead of always showing the same fixed label under the ‘Basic’ tab, the field can display different labels depending on requirements of the form. Use spreadsheet-like functions such as IF, AND, OR, etc. and make use of other field variables to set your conditions. Type @ and select the field.

This is useful when the meaning of a field changes based on context, business logic, or user choices.

For example, if you have a dropdown called AI Provider with options like “OpenAI” and “Claude”, you may want the label of your AI Block to change so that users clearly see which model or provider they are configuring.

So:
– If the user selects OpenAI, the label could change to: “OpenAI Prompt Settings”
– If the user selects Claude, the label could change to: “Claude Prompt Settings”

Formula:

IF({ai_provider} = "OpenAI", "OpenAI Prompt Settings",  "Claude Prompt Settings")

This allows the same field to adapt its displayed purpose without needing multiple separate fields.

Advanced Description

The Advanced Description option works exactly like Advanced Label, but it changes the description text instead. This is useful when guidance or instructions for a field need to change depending on earlier answers.

This helps users understand what is required from them without showing unnecessarily long or irrelevant instructions.

‍

Additional Examples (Apply to Both Advanced Label and Advanced Description)

1. Showing nothing until a selection is made

For example, if you have a dropdown field called Visit Category with options “Routine” and “Urgent”, you may want the label or description of a field to remain blank until the user first selects a category.

Once a selection is made:

• If the user chooses Routine, the field will display “Routine”.
• If the user chooses Urgent, the field will display “Urgent”.

Formula (can be used in either Advanced Label or Advanced Description):

{visit_category}The label/description stays empty until the dropdown has a selected value.
After the user picks an option, the selected text (Routine or Urgent) becomes the label or description.

2. Changing label/description based on language selection

For example, if your form includes a dropdown field called Select Language with options English, Spanish, and French, you can show the label or description in the selected language.

So:

• If the user selects English, show English text.
• If the user selects Spanish, show Spanish text.
• If the user selects French, show French text.

Formula (can be used in either Advanced Label or Advanced Description):

IF({select_language} = "English", "Enter details", IF({select_language} = "Spanish", "Ingrese detalles", "Entrez les détails"))The formula returns the text for the selected language.
Only one label/description is shown at a time, depending on what the user picks in the Select Language dropdown.

‍

Important Notes (applies to both Advanced Label and Advanced Description)

1. Variables do not change
When a field is created, its variable name is derived from the label you set in the Basic tab. That variable name is what you must use in formulas, workflows, and other logic. The visible label or description shown by Advanced Label / Advanced Description does not change the variable name.

2. Submissions tab: table view vs right panel
In the Submissions area, the table view always displays the labels from the Basic tab. When you open an individual submission, the right panel shows the labels and descriptions as they appear in the form (i.e., the Advanced Label and Advanced Description applied for that submission). This keeps the submission list consistent while letting reviewers see the context-aware labels and descriptions when viewing a record.

3. Bulk Edit shows Basic tab labels and descriptions
When you need to Bulk Edit submissions, the spreadsheet you download shows the labels and descriptions from the Basic tab only. Advanced Label and Advanced Description are not applied in Bulk Edit, so keep that in mind when preparing bulk updates.

4. Some fields cannot be used inside Advanced Label/Description formulas
Certain block types do not expose a variable that can be referenced in Advanced Label or Advanced Description. If a block does not expose a variable, you cannot use it inside the formula.

Geo Address

GPS Location

PaymentGateway

Audio

Live Tracking

Signature

Code Scanner

NFC Reader

Get Data from RestApi

Get Data from Other Apps

Get Data from Google Sheets

Get Data from Database

AI Block

Text, HTML & Embedding

Attached Files

Image Viewer

Video Viewer

PFD Viewer

Code block

Progress Bar

Action Button

‍

Display this field if

Enable this option to show/hide the Get Data from AI block in relation with another Input block. It accepts the standard Clappia Formulae, similar to conditional sections.

Allow value to be changed after initial submission

Enable this to allow the field value to be changed after submission

‍

Usage Limits and Add-on

The AI block has a limited number of included calls. If usage exceeds the limit, you can opt for additional AI calls as part of an add-on.

To increase AI usage, you can go to Workplace Settings > Billings tab and select the add on. Your AI usage can also be seen in the Billings tab.

Note

This is a beta version of the AI service available as an optional add-on. It is not included in any plan.The block uses APIs to interact with external LLMs. Use of this feature implies agreement with the terms and conditions of the selected model provider.