Custom Fibi Actions
Power up Fibi with custom actions to extend trials, update account information, get custom data, etc..
Written By Markus Palm
Last updated 6 days ago

Overview
Custom actions are one of the most powerful ways to make the Fibi AI Agent more useful for your customers. You can create completely custom workflows with external APIs to save time on your support loads.
Here are some cool workflows you could create with custom actions:
Auto-extend trials – Effortlessly manage customer trials without manual intervention.
Offer discounts – Automatically offer certain discounts to bypass budget issues.
Account insights – Quickly provide detailed customer account summaries.
Order tracking – Instantly retrieve order statuses and shipping details.
Billing & payments – Automate the retrieval of invoices or outstanding balances.
👨💻 This setup uses external APIs. If you’re uncomfortable with this, share this guide with a technical team member who can assist.
Creating your first custom action

To get started with Custom actions, head over to Dashboard → Automations → Actions. From there, click on + Create Action to create your first custom action.
The creation consists of 4 parts:
General settings – Short overview that describes the action to the AI agent
API request – Configure the API request the agent should call for this action
Test the API response – Make sure the configured API request works as expected, and provide extra instructions for the AI for result parsing
Data access – Manage whether the AI agent should get full access to the data retrieved from the API
General settings
First, define clearly when your AI agent should invoke the custom action.
Action Name: Keep it concise, descriptive, and under 50 characters. Examples:
"Extend free trial"
"Retrieve account balance"
"Check order status"
When to use: Provide clear, specific scenarios when the agent should trigger this action. Keep instructions concise (ideally under 400 characters). Examples:
"Use when a customer requests more trial time or needs their trial period extended."
"Use to quickly fetch the user's latest account balance information."
"Invoke when customers inquire about their recent order statuses."

API request
Next up, you can configure the API request that the agent will call. For this, you have the following options:
2.1. Collect data inputs from the user

List any information the AI Agent needs from the user to perform the action.
Built-in variables (email, userId, userName, userType) are automatically available if the user is authenticated in the Messenger.
Important: If you want to verify that the user is who they claim to be, check that the built-in userType variable provided for the action is equal to customer . Also, please note that this only works if you have enabled identity verification from Settings → Auth & Security → Identity verification.
2.2. Add API request details

Configure your API endpoint and request method. The URL of the endpoint also supports inputting custom variables you have available from the previous step.
For custom variables, make sure to input the name of an input from the “Collect data inputs from user” section inside two brackets e.g. {{userName}}
Full URL example with custom variable: https://api.example.com/endpoint/{{userId}}
2.3. Modify the request with data
Finally, you can pass any custom data inside the request via either query parameters, headers, or the request body.
The same custom variable syntax option is supported for all of these options.
Test the API response
Now it’s time to test the API response to make sure it works as expected.
If you used custom variables in the previous step, you’re expected to provide real example values for the variables used to simulate that the request works.

NB! The API request must be under 20KB. Anything exceeding that will return an error as the content will be too long for the AI to process.
Optional: Custom Instructions for AI
After receiving the response, you can also give extra instructions for the AI agent of how it should format it back to the user.
Data Access
Choose which API response fields Fibi can read and whether the action can run in Slack.
Choose response fields
Full data access: Gives Fibi the complete API response
Limited data access: Gives Fibi only the fields listed under Allowed Fields
For Limited access, test the request, then use 'Add Field from API Response' to select fields. You can also enter field names separated by commas.
Allowed Fields selects top-level fields. Allowing an object includes its contents. Leaving the list empty gives Fibi an empty response.
Allow the action in Slack
Under Slack access, choose:
Disabled in Slack: Keeps the action unavailable in Slack
Public-safe: Allows an action whose results are suitable for everyone in the channel
Company-safe: Restricts the action to the linked Company in an eligible Customer channel
Actions are disabled in Slack by default. The Slack channel access rules determine where each enabled option can run.
For Company-safe access, enter the exact request variable under Company ID variable, such as companyId. Use that variable in the API request. Featurebase supplies the channel’s linked Company ID; Fibi cannot choose or override it.
Important: Every channel member can read Fibi’s reply. Your API must still check authorization. A linked Company does not verify each individual Slack member.
That's it! 🎉 If you have any ideas about how we can improve custom Fibi actions, please post on our feedback board.
Was this helpful?
More in Fibi AI Agent
Fibi AI Agent overviewSet up & customize the Fibi AI agentDeployAutomatic language detection in conversationsStill need help? Ask the team