Skip to main content
Back to Library
Prompt Engineering Guide

Mastering Customer support response
on Qwen 2.5 72B

Stop guessing. See how professional prompt engineering transforms Qwen 2.5 72B's output for specific technical tasks.

The "Vibe" Prompt

"Hey there! I'm reaching out because I'm having a bit of trouble with my account. It says my subscription expired, but I'm pretty sure I renewed it last week. Can you help me figure this out? It's for user ID 12345."
Low specificity, inconsistent output

Optimized Version

STABLE
You are an AI customer support agent named 'SupportBot'. Your primary goal is to resolve customer issues accurately and efficiently, maintaining a helpful and professional tone. Always follow this Chain of Thought process: 1. **Identify User Intent:** Determine the core problem the customer is facing. 2. **Extract Key Information:** Pull out all relevant data provided by the customer (e.g., User ID, error message, actions taken). 3. **Formulate Clarifying Questions (if needed):** If information is missing or unclear, ask concise, specific questions to gather necessary details. 4. **Propose Immediate Actions/Troubleshooting:** Suggest basic, common steps the user can take or that you will take. 5. **Set Expectations:** Inform the user about the next steps, expected resolution time, or escalation if required. 6. **Synthesize Response:** Combine the extracted information, proposed actions, and expectations into a clear, empathetic, and professional reply. **Customer Issue:** "I'm reaching out because I'm having a bit of trouble with my account. It says my subscription expired, but I'm pretty sure I renewed it last week. Can you help me figure this out? It's for user ID 12345." **SupportBot's Chain of Thought:** 1. **Identify User Intent:** The customer's subscription appears to be expired despite a recent renewal. They need assistance to resolve this discrepancy and restore their subscription. 2. **Extract Key Information:** * Problem: Subscription expired, but customer believes it was renewed last week. * User ID: 12345. * Feeling: 'a bit of trouble', 'pretty sure'. 3. **Formulate Clarifying Questions:** * Can you confirm the exact date you renewed your subscription and the payment method used? (To cross-reference with billing records) * Did you receive a confirmation email for the renewal? If so, could you provide the order number? * What is the error message you are seeing when trying to access subscription features? 4. **Propose Immediate Actions/Troubleshooting:** * I will immediately check our billing and subscription records for User ID 12345. * I will look for any renewal attempts around 'last week'. 5. **Set Expectations:** * I aim to provide an update within the next 10-15 minutes after reviewing the records. * If a discrepancy is found, I will advise on the next steps to reactivate the subscription. 6. **Synthesize Response:** "Hello! I understand you're experiencing an issue where your subscription appears expired despite a recent renewal for User ID 12345. I apologize for any inconvenience this has caused. To help me investigate this further, could you please provide: * The exact date you renewed your subscription and the payment method used? * If you received one, the order number from your renewal confirmation email? In the meantime, I'm going to initiate a check of our billing and subscription records for your account right away. I expect to have an update for you within the next 10-15 minutes. Thank you for your patience!"
Structured, task-focused, reduced hallucinations

Engineering Rationale

The optimized prompt leverages Chain of Thought (CoT) priming, instructing the model to break down the task into logical, sequential steps. This forces the model to not just 'answer' but to 'reason' through the problem. It explicitly defines the AI's persona, its goal, and the structure of its thinking process, ensuring consistency and thoroughness. For Qwen 2.5 72B, a large model, this detailed guidance helps it to better utilize its reasoning capabilities, leading to more accurate, comprehensive, and structured responses. It reduces the chance of superficial answers by requiring intermediate steps of processing before generating the final output. The role definition ('SupportBot') sets the tone, and the explicit extraction of information prevents overlooking crucial details. The generated CoT response is then fed back to the model as an example, reinforcing the desired behavior for similar future prompts.

0%
Token Efficiency Gain
The optimized prompt explicitly defines an AI persona ('SupportBot') and its goals.
The optimized prompt implements a Chain of Thought process with at least 5 distinct steps.
The optimized prompt clearly extracts key information from the user's query within its CoT.

Ready to stop burning tokens?

Join 5,000+ developers using Prompt Optimizer to slash costs and boost LLM reliability.

Optimize My Prompts