Jitterbit Knowledge Agent

Overview

The Jitterbit Knowledge Agent (Knowledge Agent) is an AI agent provided through Jitterbit Marketplace that is intended to enable your organization's internal team to get intelligent answers from your organization's internal data. It does the following:

• Connects to and fetches information from the following sources using Jitterbit Integration Studio:

  • Atlassian Confluence pages
  • Atlassian Jira issues
  • Google Drive documents
  • Salesforce support cases (from the Case object)

• Integrates with Azure OpenAI to power an intelligent AI chatbot using data from the above sources accessed via a custom API created with Jitterbit API Manager.

This document explains the agent's setup and operation. It first covers prerequisites, next gives example prompts to show what the agent can do, and then provides steps to install, configure, and operate the agent.

Prerequisites

To use the Knowledge Agent, the following components are required or assumed in the design of the agent.

Harmony components

You must have a Jitterbit Harmony license with access to the following components:

• Jitterbit Integration Studio
• Jitterbit API Manager
• Jitterbit Knowledge Agent purchased as a license add-on

Azure resources

You must have a Microsoft Azure subscription with permissions to create and manage the following resources:

• Azure Storage with a Blob container to store fetched data.
• Azure AI Search with a search service that can be configured with an index and indexer.
• Azure OpenAI with a deployed gpt-4o or gpt-4.1 model.

Supported endpoints

The following endpoints are incorporated into the agent's design.

Knowledge base

You can use any or all of these endpoints as the knowledge base for this AI agent:

• Atlassian Confluence: The source of Confluence pages.
• Atlassian Jira: The source of Jira issues.
• Google Drive: The source of files stored on a Google shared drive.
• Salesforce: The source of your customer support cases from the Case object.

Chat interface

The agent's design incorporates Slack as the chat interface for interacting with the AI agent. If you want to use a different application as the chat interface, a separate workflow and instructions for a generic API setup are included in this AI agent.

Example prompts

Here are example prompts the Knowledge Agent can handle with access to the appropriate data. The agent may find information across any or all connected endpoints.

• "I am having an issue with the component 'ABC'. Can you help with this?"
• "How can I connect to a MySQL database using JDBC?"
• "Can you give me details about Jira ticket number 123?"
• "Are there any Jira tickets regarding the SQL connector?"
• "What is the security policy for installing software on my work computer?" (There may be a document on Google Drive or a Confluence page on this topic.)

Installation, configuration, and operation

Follow these steps to install, configure, and operate this AI agent:

1. Download customizations and install the Integration Studio project.
2. Review project workflows.
3. Create Microsoft Azure resources.
4. Set up a Google service account and shared drive.
5. Configure project variables.
6. Test connections.
7. Deploy the project.
8. Create the Jitterbit custom API.
9. Create the Slack app, test the Slack connection, and re-deploy the project.
10. Trigger the project workflows.

Download customizations and install the project

Follow these steps to download customization files and install the Integration Studio project for the AI agent:

1. Log in to the Harmony portal at https://login.jitterbit.com and open Marketplace.

2. Locate the AI agent named Jitterbit Knowledge Agent. To locate the agent, you can use the search bar or, in the Filters pane under Type, select AI Agent to limit the display to the available AI agents.

3. Click the AI agent's Documentation link to open its documentation in a separate tab. Keep the tab open to refer back to after starting the project.

4. Click Start Project to open a two-step configuration dialog to download customizations and import the AI agent as an Integration Studio project.

   Note

   If you have not yet purchased the AI agent, Get this agent will be displayed instead. Click it to open an informational dialog, then click Submit to have a representative contact you about purchasing the AI agent.

5. In configuration step 1, Download Customizations, the following files are provided to facilitate setup of the index and indexer in Azure AI Search and to create the Slack app. Select the files and click Download Files:

   • Azure AI Search index and indexer JSON definition files

     • Azure_AI_Search_Datasource_Definition.json
     • Azure_AI_Search_Index_Definition.json
     • Azure_AI_Search_Indexer_Definition.json

   • Slack app manifest file

     • slack_app_manifest.json

   Tip

   The configuration dialog includes a warning not to import the template before applying endpoint customizations. That warning does not apply to this AI agent and can be ignored. Follow the recommended order of steps in this documentation.

   Click Next.

6. In configuration step 2, Create a New Project, select an environment where the Integration Studio project will be created, then click Create Project.

7. A progress dialog will be displayed. Once it indicates the project is created, use the dialog link Go to Integration Studio or open the project directly from the Integration Studio Projects page.

Review project workflows

In the open Integration Studio project, review the workflows along with the descriptions below to understand what they do.

1. Data upload Utility - JIRA Ticket to Azure Index

   This workflow fetches issues from Jira, then runs the Utility - Azure Data Upload and Index workflow to upload issues to Azure Blob Storage and index them in the Azure AI Search index.

   The initial operation is Main - JIRA tickets upload. The following fields are fetched:

   "fields": [
       "summary",
       "status",
       "assignee",
       "description",
       "reporter",
       "created",
       "updated",
       "priority",
       "issuetype",
       "components",
       "comment"
    ]
   

   This workflow can be configured to fetch all issues, or only new and updated issues, using the Jira project variables.

2. Data upload Utility - SF Cases to Azure Index

   This workflow retrieves support cases from Salesforce, then runs the Utility - Azure Data Upload and Index workflow to upload cases to Azure Blob Storage and index them in the Azure AI Search index.

   The initial operation is Main - SF Cases Upload.

   In the configuration of the Salesforce Query activity, the following query retrieves support case information by agent. If your Salesforce organization doesn't use these objects and fields, or if support case information is stored in different objects and fields, this workflow will not function properly. Customize the query in this workflow to align with your Salesforce organization's data model:

   SELECT Account.Name,
          Owner.Email,
          Owner.Name,
          (SELECT CreatedBy.Email,
                  CreatedBy.Name,
                  Id,
                  CommentBody,
                  CreatedDate,
                  LastModifiedDate,
                  LastModifiedBy.Email,
                  LastModifiedBy.Name
           FROM   CaseComments),
          Id,
          CaseNumber,
          CreatedDate,
          Description,
          LastModifiedDate,
          Origin,
          Priority,
          Reason,
          Status,
          Subject,
          Type,
          CreatedBy.Email,
          CreatedBy.Name,
          LastModifiedBy.Email,
          LastModifiedBy.Name
   FROM Case
   

   This workflow can be configured to fetch all cases, or only new and updated cases, using the Salesforce project variables.

3. Data upload Utility - Confluence Pages to Azure Index

   This workflow retrieves pages from Confluence, then runs the Utility - Azure Data Upload and Index workflow to upload documents to Azure Blob Storage and index them in the Azure AI Search index.

   The initial operation is Main - Load Confluence Pages.

   This workflow fetches all Confluence pages on each execution.

4. Data upload Utility - Google Drive to Azure Blob

   This workflow retrieves files from Google Drive, then runs the Utility - Azure Data Upload and Index workflow to index them in the Azure AI Search index.

   The initial operation is Main - Google Drive Upload.

   Supported file types include Google Docs, Google Spreadsheets, and those supported by Azure Storage blob indexing.

   Supported maximum file sizes are listed as the maximum blob size in the Azure AI Search Indexer limits for your AI search service tier. For example, for the basic tier, the limit is 16 MB; for S1, the limit is 128 MB.

   This workflow can be configured to fetch all files, or only new and updated files, using the Google Drive project variables.

5. Utility - Azure Data Upload and Index

   This is a common utility workflow used by the Data upload Utility workflows to upload data to Azure Blob Storage and index it in Azure AI Search.

6. Main Entry - Slack API Request Handler

   This workflow manages incoming Slack bot requests. It is triggered via a Jitterbit custom API each time your team interacts with the Slack bot chat UI (that is, sends a Slack message to it). Configuration of the Jitterbit custom API is described in Create the Jitterbit custom API later on this page.

   If you aren't using Slack, this workflow can be ignored and won't be triggered. To use a different chat UI for your team to interact with, use the Generic API Request Handler workflow, also triggered via a Jitterbit custom API.

7. Generic API Request Handler

   This workflow processes HTTP API requests from any application. To integrate with your applications, create a custom Jitterbit API that triggers the Generic API request Handler operation. This API's URL can then be used by any application to send and receive requests.

   Configuration of the custom Jitterbit API is described in Create the Jitterbit custom API later on this page.

Create Microsoft Azure resources

Create the following Microsoft Azure resources and retain the following information for configuring the AI agent. To create and manage these resources, you must have a Microsoft Azure subscription with the appropriate permissions.

Azure Blob container

You must create an Azure Blob container to store customer details. Data from the Blob container will be indexed in Azure AI Search using an index and indexer.

You'll need the container's SAS URL for use in determining the values of the Azure Blob Storage project variables. To generate the SAS URL:

1. In the Azure portal, browse to Storage accounts and open the specific storage account.
2. From the resource menu under Data storage, select Containers and open the specific container.
3. From the resource menu under Settings, select Shared access tokens.

4. Use the Permissions menu to verify that the shared access signature (SAS) URL for this container has a minimum of Read and Write permissions:

   

5. Click Generate SAS token and URL.

6. Copy the Blob SAS URL displayed at the bottom.
7. Determine the values of the Azure Blob Storage project variables from the SAS URL. The SAS URL is in the format of {{ azure_blob_base_url }}/{{ Azure_Blob_Container_Name }}?{{ azure_blob_sas_token }}.

If using the JSON definition files included in the AI agent's customization files to generate the index and indexer, you'll also need the Azure Blob Storage account key. To view account access keys:

1. In the Azure portal, browse to Storage accounts and open the specific storage account.
2. From the resource menu under Security + networking, select Access keys.

3. Click Show keys to reveal the access key to use during configuration of Azure AI Search.

   

Azure AI Search service

You must create an Azure AI Search service and configure its index and indexer to process the data from the Blob container.

You'll need the Azure AI Search service's URL and API key to determine the values of the Azure AI Search project variables:

• URL: To obtain the value to use for azure_ai_search_url, refer to the Azure documentation Get service information.
• API key: To obtain the value to use for azure_ai_search_api_key refer to the Azure documentation Configure role-based access.

You can use the JSON definition files included in the AI agent's customization files to generate the index and indexer, or you can create them yourself.

If using the provided definition files, you must replace the following placeholders with your own configuration values:

Azure_AI_Search_Indexer_Definition.json

Azure_AI_Search_Datasource_Definition.json

Azure OpenAI resource

You must create an Azure OpenAI resource and deploy a gpt-4o or gpt-4.1 model via the Azure AI Foundry portal.

You'll need the deployment name, Azure OpenAI endpoint URL, and API key to determine the values of the Azure OpenAI project variables. To find these values:

1. In the Azure AI Foundry portal, open the specific OpenAI resource.

2. The values to use for the endpoint URL (azure_openai_base_url) and API key (azure_openai_api_key) are displayed on the landing page for the resource:

   

3. In the navigation menu under Shared resources, select Deployments. The deployment name (Azure_OpenAI_Deployment_Name) is displayed.

Set up a Google service account and shared drive

This setup is required only if you're using Data upload Utility - Google Drive to Azure Blob workflow. You must have an active Google Cloud project to proceed. If you don't have one, you can create one by following Google's instructions.

Create a Google service account

Follow the steps below to create a key for the Google service account to allow the utility to securely access your Google Drive files:

1. In the Google Cloud console, use the search bar to find and navigate to the Service Accounts page.

2. If you already have a service account you want to use, proceed to step 3. Otherwise, click Create service account, provide a name, and click Done. No additional permissions or access are needed.

   

3. Select the service account to open its Service account details:

   

4. Navigate to the Keys tab and use the Add key menu to select Create new key.

   

5. Choose JSON as the key type and click Create. A JSON file containing the credentials will download to your computer.

6. Open the downloaded JSON file to find the following values needed to configure the Google Drive project variables:

   • client_email: This is the value for the Google_Client_Email project variable and needed to configure the Google shared drive in the next section.
   • private_key: This is the value for the Google_Private_Key project variable.

7. Enable the Google Drive API in your Google Cloud account:

   1. In the Google Cloud console, use the search bar to find and navigate to the APIs & Services page.

   2. Access the API Library and select the Google Drive API:

      

   3. Click the Enable button:

      

Configure the Google shared drive

The Google shared drive should be configured as follows to allow the utility access to any files you upload to it:

1. Create a Google shared drive if you don't already have one.

2. Open the shared drive and copy its ID from the browser's URL. The ID is the long string of characters at the end. For example, if the URL is https://drive.google.com/drive/folders/dftg-LbGrP7hdfd, the ID is dftg-LbGrP7hdfd. This ID is the value for the Google_Drive_ID project variable when configuring Google Drive project variables.

3. Click the name of the shared drive at the top of the page and select Manage members. A dialog appears.

4. In the Add people and groups field, paste the value of the client_email from the JSON file you downloaded earlier.

5. Assign the Content manager role to the service account and confirm the action.

Configure project variables

In the Integration Studio project installed earlier via Marketplace, you must set values for the following project variables.

This can be done using the project's actions menu to select Project Variables to open a drawer along the bottom of the page where you can review and set the values.

Salesforce

Jira

Confluence

Google Drive

Azure Blob Storage

Azure AI Search

Azure OpenAI

Slack

Common

Test connections

Test the endpoint configurations to verify connectivity using the defined project variable values.

This can be done from the design component palette's Project endpoints and connectors tab by hovering on each endpoint and clicking Test.

Deploy the project

Deploy the Integration Studio project. This can be done using the project's actions menu to select Deploy.

Create the Jitterbit custom API

Create a custom API using API Manager for one of the following:

• Slack bot API request handler: Required if using the Slack notification included in the design of this AI agent.
• Generic API request handler: Optional. Use for handling API requests from any application.

Create the Slack bot API request handler

This custom Jitterbit API will trigger the Slack Bot API Request Handler operation. Configure and publish the custom API with the following settings:

• API Service: Slack Bot API Request Handler
• Path: /
• Project: Select the Integration Studio project created from the Jitterbit Knowledge Agent in Marketplace
• Operation to Trigger: Slack Bot API Request Handler
• Method: POST
• Response Type: System Variable

Retain the service URL of the published API for use in creating the Slack app. The service URL can be found in the API details drawer on the Services tab by hovering on the service's Actions column and clicking Copy API service URL.

Generic API request handler

This custom Jitterbit API will trigger the Generic API request Handler operation. It is not required. Create this API if you are using other applications to process HTTP API requests. Configure and publish the custom API with the following settings:

• Service name: Generic API request Handler
• Project: Select the Integration Studio project created from the Jitterbit Knowledge Agent in Marketplace
• Operation: Generic API request Handler
• Method: POST
• Response type: System Variable

{
    "username": "johnr",
    "prompt": "How to connect to mysql using a connector?"
}

{
    "message": "To connect to a MySQL database using the Database connector, follow these steps:   - Use the MySQL JDBC driver that ships with the agent for additional features like manual queries.",
    "references": [],
    "status_code": 200
}

Create the Slack app, test the connection, and re-deploy the project

To create the Knowledge Agent chat interface in Slack, create a Slack app using the Slack app manifest file provided with this AI agent's customization files. Or, create it from scratch.

If using the provided Slack app manifest file (slack_app_manifest.json), you must replace the following placeholders with your own configuration values:

After installing the Slack app, obtain its bot token.

Re-open the project variables configuration and enter the bot token for the Slack_Bot_Token project variable value.

Once the bot token is set, test the Slack connection and re-deploy the project.

Trigger the project workflows

For the initial data load, run any or all of the Data upload Utility workflows depending on your data sources. This can be done using the initial operation's Run option shown by hovering on the operation. You will need to run the operation again in the future if your data is updated.

The two other main workflows are triggered by the Jitterbit custom APIs:

• Main Entry - Slack API Request Handler: This workflow is triggered from Slack via the Slack Bot API Request Handler custom API. Sending a direct message to the Slack app will initiate the custom API trigger.

• Generic API Request Handler: This workflow is triggered from another application via the Generic API request Handler custom API. Sending a request to the configured API will initiate the custom API trigger.

All other workflows are triggered by other operations and are downstream of those listed above. They are not intended to be run by themselves.

Troubleshooting

Review API logs and operation logs for detailed troubleshooting information.

For additional assistance, contact Jitterbit support.