What is the AI Studio?

SINCE 11 - BETA

The AI Studio is a set of tools and UI components seamless integrated into PIPEFORCE to boost your process automation and data integration tasks to a next level using artificial intelligence such as LLM (Large Language Models) for example.

Configure AI Backend (secret)

Before you can start, an AI backend needs to be configured. Depending on your license, by default PIPEFORCE comes with it’s own built-in AI backend which is located in Germany.

If you do not specify otherwise, this AI backend is used by default.

But you can switch this default backend or use multiple AI backends in parallel. To do so, you have to configure the credentials and settings for those AI backends as secrets of type secret-text and place a JSON into the secret value which has a structure like this:

{
  "base_url": "string",
  "model": "string",
  "api_token": "string",
  "max_token": "integer",
  "custom_headers": { "name": "value" }
} 

Whereas:

• base_url: The base url of the API (requried).

• model: The AI model to be used (required).

• api_token: The security token to be used.

• max_token: The max token to be send (defaults to 800)

• custom_headers: Key-value pairs to be passed along as HTTP headers on any request.

Connect to OpenAI (ChatGPT)

In case you would like to connect to the OpenAI services for example, you could use these settings in your secret:

{
  "base_url": "https://api.openai.com/v1",
  "model": "gpt-3.5-turbo",
  "api_token": "your_token",
  "max_token": 800
} 

Text-to-Command

This powerful feature of the AI Studio takes a non-structured text such as an email, a chat message or a PDF document for example, analyses it using AI and then automatically detects and executes the according PIPEFORCE command including its parameters which must be executed in order to take action and fulfill the use request.

Here are some examples where this feature could be helpful:

• Automatically forward emails to the responsible internal team
  Scan any email sent to a given inbox such as info@mycompany.tld for example, find out the intention of the sender, then forward the email to the internal team such as support, sales, … which can handle the request. The AI can find out whether it is a support request, an order request, a question regarding an invoice or any other types just by writing an advice without any programming. It can also automatically detect and extract all required data such as customerId, invoiceNumber and more from the email and pass it along with the internal email.

• Automatically start an internal workflow by email
  Scan any email sent to a given inbox such as invoice@mycompany.tld for example and if this email matches to an existing workflow, extract all variables required for this workflow from the email, start the workflow and pass these variables along with it. For example to start an accounts payable workflow based on an given payable invoice.

• Automatically call endpoints of other systems by email
  Scan any email sent to a given inbox such as info@mycompany.tld for example and if this email is related to a service, offered by a third party system which provides an remote API, call this remote API (for example REST) and pass along parameters extracted from the email. For example create a new ticket on an external ticket system.

Using command ai.intent.detect

In order to integrate Text-to-Command functionality into your automation pipelines, you can use the command ai.intent.detect. It will take a text like an email as input, will apply the given AI instructions on this text and finally will select a command to be executed. Here is a first example how to use it:

body: |
  From: customer@somedomain.tld
  Subject: I have a problem with your product
  Hello,
  I have a big problem with your product and need support.
  My customer id is 123456.
  Cheers, Valued Customer
  
pipeline:
  - ai.intent.detect:
      advice:
        intentCandidates:
          - intentId: "forwardToSupport"
            description: "Use this intent in case the sender needs product support."
            commandName: "mail.send"
            parameters:
              to:
                name: "to"
                value: "support@internal.tld"
                commandParameter: true
              from:
                name: "from"
                description: "The email address of the sender."
                detect: true
                commandParameter: true
              subject:
                name: "subject"
                description: "Use the subject of the sender's email."
                detect: true
                commandParameter: true
              message:
                name: "message"
                description: "Use the message of the sender's email."
                detect: true
                commandParameter: true
          - intentId: "forwardToInfo"
            description: >
              Use this intent in case the sender's intent could not be detected.
            commandName: "mail.send"
            parameters:
              to:
                name: "to"
                value: "info@internal.tld"
                commandParameter: true
              from:
                name: "from"
                description: "The email address of the sender."
                detect: true
                commandParameter: true
              subject:
                name: "subject"
                description: "Use the subject of the sender's email."
                detect: true
                commandParameter: true
              message:
                name: "message"
                description: "Use the message of the sender's email."
                detect: true
                commandParameter: true

As you can see in this example, there are two command intents configured:

• One intent will forward the customer email to the support team (=forwardToSupport) and

• the other one to the info team in case it is related to any other topic (= forwardToInfo).

Each intent has an advice description in order to instruct the AI about the criteria to select this intent. In case such an intent is selected by AI, there is the commandName field defining the name of the command which must be finally called. In this example this is the mail.send command.

The parameters section on each intent lists the parameters required to call the command. For the mail.send command these are the parameters to, from, subject and message. For each command it can be configured whether the AI should auto-detect the value (detect: true, as you can see for the from parameter for example), in this case the description field is mandatory to instruct the AI how to extract the parameter. Or it can be a fixed value (as you can see for the to parameter for example).

In order to keep this example simple, we set an email text at the very beginning in the body. This text will be passed to the AI for analysis using the given advice.