Support template
Ticket classification prompt template
Route a message to exactly one category with a confidence. Routing tickets or messages to queues, where your code needs exactly one label and a confidence to decide on human review.
The prompt
prompt.md
## Task
Classify the support message below into exactly one category: billing, bug, feature_request, account_access, or other.
## Requirements
- Choose "other" when no category clearly applies.
- Base the decision only on the message text.
## Output format
Return only valid JSON with the keys category and confidence, where confidence is a number from 0 to 1.
## Input
<message>
{{message}}
</message>Variables
| Variable | What to pass in |
|---|---|
{{message}} | The message to classify, exactly as received. |
Each variable sits inside its own tags so the model treats what you insert as data, not instructions.
How it scores
100/100 with no warnings or critical issues, checked in CI on every change.
| Dimension | Score |
|---|---|
| Clarity | 100 |
| Specificity | 100 |
| Completeness | 100 |
| Structure | n/a |
| Consistency | 100 |
| Output specification | 100 |
| Efficiency | 100 |
| Security | 100 |
Tokens and cost per model
Input tokens for the template itself, before you fill in the variables. Costs use reference prices; verify with your provider.
| Model | Tokens | Input cost / 1,000 calls |
|---|---|---|
| GPT-4.1 | 90 | $0.1800 |
| GPT-4.1 mini | 90 | $0.0360 |
| Claude Sonnet 5.5 | 90 (approx.) | $0.1800 |
| Claude Haiku 4.5 | 90 (approx.) | $0.0900 |
| Gemini 2.5 Flash | 90 (approx.) | $0.0270 |
Adapting it
- Replace the category list with your own, and keep an explicit fallback such as "other".
- Send low-confidence results (for example under 0.6) to a human queue in your code, not in the prompt.
- Add one short definition per category if two categories are easy to confuse.
After editing, the workspace re-scores the prompt as you type and flags anything that regresses.
More templates
- Pull request review: Structured review of a diff with severity-ranked findings.
- Customer support reply: On-policy reply to a customer ticket with a fixed structure.
- Structured data extraction: Extract fields from free text into a strict JSON object.
- Meeting summary: Decisions, owners, and deadlines from a transcript.
- Tool-using agent system prompt: Scoped agent with explicit tool rules and a stop condition.