Guide
Fibery AI in Automations integrates Fibery with GPT (we use OpenAI). It works in Text, Number and Rich Text fields.
https://youtu.be/ONlWc6tBReg
Use Cases
Here are some use cases that you may find useful.
Summarize conversations/meetings/chats/emails/…
You can have Summary field for Intercom Conversation and it will be filled automatically via Summarize command, same can be applicable to meeting notes, and other databases. Then you can create a Feed View that shows just Summary field.
Sentiment Score of a conversation
Analyze sentiment of a conversation, set some score into Sentiment Score field and calculate average or draw trends charts, or spot conversations with bad sentiments and do something about it.
Sentiment scores are a metric for measuring customer sentiment. Scores can range from 0-100, where 100 is the most positive possible outcome and 0 is the least. Generate a sentiment score for the text below and return result as a number in a format [sentiment score] without brackets
"""
{{Messages}}
"""
Extract data into fields
Extract Zip, Country and City from messy address field and put it into Zip Code Field.
For example, you have a raw address field in a Contact database where you store addresses like Australia, 2106 Sydney, Wakefield St. 6, then you can use Call AI function to extract City, Country and Zip code from this raw address and put them into separate fields.
Extract city from the address {{raw address}}
Translate a support chat to English
Sometimes we communicate with customers in other languages, like Russian. However, it is much better to store communications in Fibery in a single common language. Thus when the chat is closed, it can be automatically translated to English translated content can be set to a new Field like English Version.
As a simple solution there can be two commands.
Detect a language and set it into a Language field
Create command Translate to {{Language}}
Generate sample data
Provide some samples to AI and ask to generate a set of similar entities. For example, here it generates entities with some generate on the fly address.
Here is the prompt example:
Here are some addresses as an examples:
Antheon 7, 4520 Limassol, Cyprus
POLAND,01-106 Warsaw, Nakielska 7/C
USA, 3345 Boston, High str. 1
Generate a sample address based on the examples above
https://www.loom.com/share/9328e4d1c6834d14a0a5c4db6462a6fa
Call AI Action in fields
Admin can configure parametrized prompts to GPT that will return some text and Fibery will put this text into fields.
Only the following field types are supported so far:
Text
Number
URL
Phone
Email
Rich Text
If you want to set some Text or Number field from GPT response, click … near Field on the right and select Call AI option.
Then set a prompt. Prompt can be parametrized, like {{Name}} or {{Feature.Name}} can be added into it for the current entity. For example, we have a Country and want to set Capital field automatically based on GPT response. Here is how you can do it:
How to test prompts?
Use AI Text Assistant to test prompts.
When it works fine, create a Button or Rule with the prompt.
AI function in rich text templates
You can call AI function like in Markdown Templates, like this:
[ai temperature=0.5 maxTokens=300 model=gpt-4o]
Generate a small post about {{Name}}
[/ai]
Possible parameters:
temperature from 0 to 1. Temperature is a parameter used to control the randomness of the generated text. It is a number between 0 and 1. A lower temperature will cause the model to make more predictable choices, while a higher temperature will cause the model to take more risks and generate more diverse and interesting text.
maxTokens from 1 to 2048. Defines response size.
model sets OpenAI model. Default is gpt-5-mini
List of models you can use in automations: gpt-4o-mini, gpt-4o, chatgpt-4o-latest, gpt-5, gpt-5-chat-latest, gpt-5-mini
For example, here is the action button setup that summarizes Messages field in Intercom Conversation.
The good thing about action buttons is that you can execute them in batches. Select some rows in Table View, click Actions and run the action.
Summarize Comments thread
Here is the template script that summarizes comments. Put it into some Rich Text Field that should contain comments summary.
[ai temperature=0 maxTokens=300 model=gpt-4o]
"""
{- Comments:Text -}
"""
Generate summary of the conversation above
[/ai]
AI in formulas in automations
You can generate formulas using AI in automation rules as well.
FAQ
How expensive is it?
On the free plan, you can use AI to create databases, views, formulas an automation scripts.
Full AI is included in every paid plan, but the limits vary. Check out the details here.