...

Each task consists of components that also run in sequence, ensuring a structured execution process. The typical internal flow follows these steps:

1. PromptPrompts:
   The system first sends the defined prompt to the LLM (Large Language Model). Multiple prompts placed within one task will also run sequentially.

2. Tools (Optional):
   If the response requires additional functionality, such as calling an API, retrieving data, or executing database queries,the appropriate tool is invoked after the prompt.

3. Enhancers (Optional):
   Once the output is generated (after Prompt + Tool), Enhancers are triggered last. These allow you to store the output in a form field, process a variable, or modify the result before final use.
   

...

You can download the AI Agent Builder plugin from the Joget Marketplace.

How to install

1. Download the plugin JAR file from the Joget Marketplace. 
2. Go to your Joget localhost or server. In the Joget Console, go to Admin Bar > Systems Settings > Manage Plugins and click the Upload Plugins button.
3. Under Upload Plugin, select the plugin .jar file you downloaded and click Upload.
4. Once uploaded, the plugin will be available in your Joget environment.

...

1. In a new app or an existing app, navigate to the App Composer.
2. Under AI Agent, click the ADD NEW button to create a new AI Agent.
   
   
3. Provide an ID, Name, and Description for the API connector, and click Save.
   
   
4. When the AI Agent Builder is launched, you will see a Define Agent action and a First Task section.
   
5. Under Define Agent, click LLM Service to configure a large language model. Since OpenAI is currently the only supported model, configure the following:
   1. For Model, select an OpenAI model.
   2. For API Key, specify an LLM key obtained from OpenAI.
   3. Optionally, for Proxy Domain, if your environment routes API calls through a proxy, specify the domain here.
   4. Click Apply Changes.
      
      
6. By default, a Persona prompt is in the Define Agent section. You may delete by clicking the Remove button and replace it with a new prompt by dragging and dropping it from the palette. If you choose to retain it, you can configure it by clicking on it:
   1. For Role, specify the position, character, or responsibility the AI is expected to take on. By default, it is Research Analyst & Tech Writer.
   2. For Backstory, specify a brief background or experience for the AI to adopt, which helps add realism or specific domain knowledge. The default values are:
      Your writing is insightful, well-researched, and future-oriented, with a focus on:
      - Technical deep dives
      - Industry impact analyses
      - Ethical and societal discussions
      - Comparative studies
      Your goal is to educate and inspire businesses, researchers, and enthusiasts about ${query}.
      
   3. Click Apply Changes.
      
      
7. Under First Task, a default Text Prompt is in the Drop a prompt to here section. You may delete it or configure it if you choose to retain it.
8. Drag and drop a tool from the Tools section of the palette into the Drop a tool to here section. Click on the tool to configure it.
   
   
9. Drag and drop an enhancer from the Enhancers section of the palette into the Drop an enhancer to here section. Click the enhancer to configure it.
   
   
10. If needed, you can rename the First Task section to any desired name by clicking on the section, specifying a Task Name, and clicking Apply Change.
    
    
11. Additionally, you can add a New Task section by clicking the Add Task button beside existing tasks.
    
    
    
12. Configure you AI Agent inputs in the Settings tab. Refer to AI Agent Builder Properties for more information.
    Image Added
    
13. In the Preview tab, test your AI Agent to ensure it generates a response correctly.
    Image Added
    After clicking Run Agent, a response is generated as follows:
    • Content: This refers to the actual data being transmitted in a request or response.
    • Request Payload: This is the data sent by the client to the server in an HTTP request. It usually contains information needed for processing, such as form inputs or JSON objects in a POST or PUT request.
    • Full Response: This includes everything returned by the server in response to a request. It consists of the status code, headers, and the response body (which contains the actual content).
      Image Added
14. Click Click Save to save the AI Agent.
    
    

...

• Refer to AI Agent Builder Element for all configuration properties for Prompts, Tools, and Enhancers.
• Refer to AI Agent Builder Properties for AI Agent Builder properties in the Settings tab.

Expected Outcome

After configuring an AI Agent, the AI Agent can now be incorporated into a Joget App as a Process tool in Process Builder or as a post-processing tool in Form Builder. Refer to to AI Agent Tool (Process Builder) for  for more information.

Download plugin

...