Agentic Leasing

Agentic Leasing is a fully agentic business application built on DRUID technology and powered by LLM. It offers a smooth, conversational experience for managing leasing operations. Users can interact naturally with the assistant to generate documents, review invoices and partner details, make payments, and handle more complex tasks like early terminations or partial reimbursements.

Key Components

This solution includes:

  • A back-end Leasing database powered by DRUID Data Services.
  • A workspace for leasing agents to view and process user requests.
  • A set of LLM-powered agents that automate leasing workflows and user interactions.

Business Workflow

  1. Conversational Leasing Support. The assistant helps users complete tasks such as generating travel or damage authorizations, reviewing due or unpaid invoices, accessing partner details, and making payments.
  2. Ticket-Based Flows. For more complex processes such as early termination or partial reimbursement, the assistant collects the necessary details from the user and generates a support ticket. These tickets are stored in the back-end database, where human agents can review, process, and close.

Prerequisites

  • Tenant Druid community (open new tenant here) or Druid subscription.
  • You should have a Druid bot. For information on how to create a bot, see Creating Druid Bots.
  • Enable the API Resources for Druid WebView and Druid Data Service. Then, activate the Druid Data Service in your tenant by navigating to Administration > Settings > Druid Data Service, and selecting Is enabled and clicking the Save all button at the top right of the page.
  • You need to have the gpt-4.1 and gpt-4o-mini models deployment via Microsoft Azure, OpenAI, or other LLM provider that supports tools / function calling. If you want to use these models via DRUID LLM API resources, they must be activated for Azure OpenAI (models gpt-4.1 and gpt-4o-mini) on your tenant. Contact your DRUID sales representative to enable DRUID-dedicated resources and generate an API token for Druid.LLM.

Configuring the Skill Template

To configure the skill template, follow these steps:

Step 1. Install the solution from the Solutions Library

Go to the Solutions Library, search for solution DRUID-LLM Leasing Assistant and import it following the instructions provided in section Installing Solution Templates.

Wait until the import status shows as “Success”.

Step 2. Configure apps connections

Go to solution Apps and configure the following three connections with your credentials:

App Description Setup required
Druid_Sendgrid Used to send emails to users. Enter the SendGrid API key. Mandatory
Druid-LLM 4.1

Provides integration with GPT-4.1, which is not included as a standard feature in DRUID. Configure this app to connect it to your own GPT-4.1 deployment (via Microsoft Azure, OpenAI, or other LLM provider that supports tools / function calling).

 Mandatory
Druid-LLM 4.1 mini

Provides integration with GPT-4.1 mini, which is not included as a standard feature in DRUID. Configure this app to connect it to your own GPT-4.1 mini deployment (via Microsoft Azure, OpenAI, or other LLM provider that supports tools / function calling).

 Mandatory

After you configure the connections, click Publish.

Step 3. Set up the bot special flows

  1. Go to the bot settings, Details page.
  2. Click the Dialog Management section header.
  3. In the Welcome flow field, select "welcome-flow".
  4. In the Intent not found flow field, select “switch-intent”.

  5. Save the changes.

Step 4. Configure NLU Intents Classification with LLM

To configure NLU intents classification with LLM, follow these steps:

  1. Navigate to NLU > Configurations > Intents tab.
  2. Click on Thresholds and parameters.
  3. Add the NLU.NER.Classification.ModelType parameter and set it to LLM.

    4. Click the link that appears in the message below the NLP parameters. The NLU Intents Classification with LLM section expands.

  4. From the Endpoint Type field, select Druid.
  5. From the Model Name field, select Druid/becus1.0 or another DRUID LLM.
  6. For both prompts, click the Set default button. The default DRUID prompts will be automatically filled in.

  7. Click Save at the bottom of the page to apply the NLU configuration.
  8. Train the bot.

Step 6. Run database setup workflow

Open a new web chat to trigger the database setup workflow. The virtual assistant will automatically run the workflow, adding all necessary LLM prompts and demo data to the Leasing database.

Once the setup is complete, your assistant is ready for use in real-world leasing interactions.