Reduce LLM spend by prompt engineering

Classify this customer email into one category:

TECHNICAL_SUPPORT: bugs, crashes, sync issues, app problems
BILLING_INQUIRY: payments, invoices, refunds, subscription questions
SALES: demos, pricing, partnerships, new customer inquiries

Route to: mobile dev team, billing team, sales team, or escalation team

Respond in JSON:
{"category": "", "department": ""}

You are a professional email classification system for customer support operations.
Your task is to accurately categorize incoming emails and route them to appropriate
departments for optimal response times and customer satisfaction.

CLASSIFICATION CATEGORIES:

1. TECHNICAL_SUPPORT:
   - Application bugs, crashes, freezing, performance issues
   (additional categories omitted)

curl -X POST 'https://api.narev.ai/v1/traces/cost' \
  -H 'Content-Type: application/json' \
  -d '{
    "model_id": "gpt-oss-20b",
    "provider_id": "openai",
    "usage": {
      "prompt_tokens": 225,
      "completion_tokens": 25
    }
  }'

curl -X POST 'https://api.narev.ai/v1/traces/cost' \
  -H 'Content-Type: application/json' \
  -d '{
    "model_id": "gpt-oss-20b",
    "provider_id": "openai",
    "usage": {
      "prompt_tokens": 443,
      "completion_tokens": 25
    }
  }'