1. **Multi-Class Support Ticket Routing**
   Input a batch of 50 synthetic customer service emails involving various issues (e.g., "password reset," "damaged shipment," "billing discrepancy," "feature request"). The model must classify each email into one of five predefined categories and assign a priority level (P0 to P3) based on the perceived urgency and customer sentiment.
   *Metric: Classification Accuracy, Priority Alignment, and Latency per Email.*

2. **Thread Summarization and Action Item Extraction**
   Provide a long, multi-turn email thread (10+ replies) between three different departments (e.g., Engineering, Marketing, and Legal) discussing a project delay. The model must produce a 3-sentence executive summary of the current status and a bulleted list of specific action items, including the assigned owner for each task.
   *Metric: ROUGE Score (Summary), Action Item Recall, and Entity Extraction Accuracy.*

3. **Sales Lead Qualification & Intent Analysis**
   Input a series of "Contact Us" inquiries from potential B2B clients. The model must analyze each inquiry to determine if the lead is "Hot" (ready to buy), "Warm" (researching), or "Cold" (unqualified). It must also extract key data points such as estimated budget, company size, and desired timeline.
   *Metric: Precision/Recall on "Hot" leads and Field Extraction Accuracy.*

4. **Phishing and Social Engineering Detection**
   Present a set of emails, some of which contain subtle social engineering tactics (e.g., "urgent" requests for gift cards, spoofed internal HR announcements, or suspicious links). The model must identify which emails are malicious and provide a brief "Reasoning" statement for each flag, highlighting the specific red flags found.
   *Metric: False Positive Rate and Reasoning Coherence.*

5. **Sentiment Trend Mapping & Feedback Aggregation**
   Provide a collection of 100 short feedback emails regarding a recent software update. The model must aggregate these into a structured report that identifies the top three most common complaints, the overall sentiment trend (Positive, Neutral, Negative), and three specific feature recommendations based on the feedback.
   *Metric: Sentiment Alignment, Unique Issue Identification Count, and Recommendation Relevance.*