Skip to main content

Use Case Examples

These examples show Supervised Intelligence in action. The LLM handles language. The platform controls decisions, executes actions, and produces an auditable record.

Customer Support​

Order Status Lookup​

Scenario: Customer wants to track an order.

Conversation:

Customer: Where is my order?

Agent: I can help with that. What is your order number?

Customer: ORD-58291

Agent: Found it. Order ORD-58291 is in transit.
       Carrier: FedEx
       Last update: Arrived at local facility (Chicago, IL)
       Expected delivery: Tomorrow by 8pm

       Do you want tracking updates by SMS or email?

Behind the scenes:

  • collect order_id
  • action orders.get-status
  • choice notification channel
  • done with status summary

Return And Refund​

Scenario: Customer wants a refund.

Conversation:

Customer: I want to return my shoes.

Agent: I can help. What is the order number?

Customer: ORD-99112

Agent: Thanks. This order is within the return window.
       Do you want a refund to the original payment method or store credit?

Customer: Original payment method.

Agent: Please confirm you want to return order ORD-99112 for a refund.

Behind the scenes:

  • collect order_id
  • action orders.get-details
  • action returns.check-eligibility
  • choice refund method
  • confirm before write action
  • action returns.create
  • done with confirmation

Technical Support​

Device Troubleshooting​

Scenario: Device is offline.

Conversation:

Customer: My thermostat will not connect to WiFi.

Agent: I will guide you through a few steps. First, what model do you have?

Customer: T3007ES

Agent: Thanks. Step 1: Open Settings and select Network. What do you see?

Behind the scenes:

  • collect device_model
  • guide step by step instructions
  • Knowledge search for model specific steps
  • Optional investigate using read actions for diagnostics

Sales And Lead Qualification​

Demo Booking​

Scenario: Visitor wants an enterprise demo.

Conversation:

Visitor: I want an enterprise demo.

Agent: Great. What is your company name and team size?

Visitor: Acme Corp, 200 agents.

Agent: Thanks. What is your main use case?
       1. Customer support
       2. Sales assistance
       3. Internal helpdesk

Visitor: Customer support.

Agent: Understood. I can book a demo. Do you prefer Tuesday or Thursday?

Behind the scenes:

  • collect company_name, team_size
  • choice use case
  • action calendar.check-availability
  • action calendar.book
  • done with confirmation

Why These Work​

  • Natural language is handled by the LLM
  • Decisions are controlled by the platform
  • Actions execute only when conditions are met
  • Every step is auditable

Next Steps​