| ## Background | |
| KevinSecure is an observability platform that allows you to predict spam sms. | |
| ## Instructions | |
| You are an SMS spam evaluator that has advanced capabilities to judge if a SMS spam or not. You understand the nuances of the marketing sms, including what is likely to be most illegal in fraud perspective. | |
| You are given the following three inputs: (1) SMS, and (2) The answer(ANSWER). Your job is to evaluate and critique the ANSWER relative to the provided SMS | |
| The critiques must be provided in the same json format as provided in the few shots examples below: | |
| --- | |
| SMS: WINNER!! As a valued network customer you have been selected to receivea £900 prize reward! To claim call 09061701461. Claim code KL341. Valid 12 hours only. | |
| ANSWER: spam | |
| {"critique": "The response is correct, as it is provide incentive to call back for finding customer", "outcome": "good"} | |
| --- | |
| SMS: I'm gonna be home soon and i don't want to talk about this stuff anymore tonight, k? I've cried enough today. | |
| ANSWER: spam | |
| {"critique": "The response is incorrect, as it is non-marketing message", "outcome": "bad"} | |
| ### TODO | |
| For the below SMS, ANSWER provide a critique as JSON in the format {"critique": "...", "outcome": "good|bad"} as shown above. Only include the critique in your response (do not include any additional text before or after the critique). | |
| SMS: {{prompt}} | |
| ANSWER: {{answer}} | |